Skip to yearly menu bar Skip to main content


Workshop

Safe Generative AI

Dianbo Liu ⋅ Ling Pan ⋅ Tailin Wu ⋅ Bonaventure F. P. Dossou ⋅ Emmanuel Bengio ⋅ Yilun Du ⋅ Dinghuai Zhang ⋅ Yoshua Bengio
Project Page [ OpenReview] 

Abstract

Video

Chat is not available.

Schedule

Timezone: America/Los_Angeles
11:40 AM
Lunch break
3:00 PM
Poster session
3:00 PM
Poster session
HSpace Sparse Autoencoders
Ayodeji Ijishakin ⋅ Ming Ang ⋅ Levente Baljer ⋅ Daniel Tan ⋅ Hugo Fry ⋅ Ahmed Abdulaal ⋅ Aengus Lynch
Measuring Steerability in Large Language Models
Trenton Chang ⋅ Jenna Wiens ⋅ Tobias Schnabel ⋅ Adith Swaminathan
Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge
Jiayi Ye ⋅ Yanbo Wang ⋅ Yue Huang ⋅ Dongping Chen ⋅ Qihui Zhang ⋅ Nuno Moniz ⋅ Tian Gao ⋅ Werner Geyer ⋅ Chao Huang ⋅ Pin-Yu Chen ⋅ Nitesh Chawla ⋅ Xiangliang Zhang
Towards Safe and Honest AI Agents with Neural Self-Other Overlap
Marc Carauleanu ⋅ Michael Vaiana ⋅ Diogo de Lucena ⋅ Judd Rosenblatt ⋅ Cameron Berg
Towards Safe and Honest AI Agents with Neural Self-Other Overlap
Marc Carauleanu ⋅ Michael Vaiana ⋅ Diogo de Lucena ⋅ Judd Rosenblatt ⋅ Cameron Berg
Model Pairing Using Embedding Translation for Backdoor Attack Detection on Open-Set Classification Tasks
Alex Unnervik ⋅ Hatef Otroshi Shahreza ⋅ Anjith George ⋅ Sébastien Marcel
Model Pairing Using Embedding Translation for Backdoor Attack Detection on Open-Set Classification Tasks
Alex Unnervik ⋅ Hatef Otroshi Shahreza ⋅ Anjith George ⋅ Sébastien Marcel
Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models
Neel Jain ⋅ Aditya Shrivastava ⋅ Chenyang Zhu ⋅ Daben Liu ⋅ Alfy Samuel ⋅ Ashwinee Panda ⋅ Anoop Kumar ⋅ Micah Goldblum ⋅ Tom Goldstein
GuardFormer: Guardrail Instruction Pretraining for Efficient SafeGuarding
James O' Neill ⋅ Santhosh Subramanian ⋅ Eric Lin ⋅ Abishek Satish ⋅ Vaikkunth Mugunthan
GuardFormer: Guardrail Instruction Pretraining for Efficient SafeGuarding
James O' Neill ⋅ Santhosh Subramanian ⋅ Eric Lin ⋅ Abishek Satish ⋅ Vaikkunth Mugunthan
Hidden in the Noise: Two-Stage Robust Watermarking for Images
Kasra Arabi ⋅ Benjamin Feuer ⋅ R. Teal Witter ⋅ Chinmay Hegde ⋅ Niv Cohen
Auditing Empirical Privacy Protection of Private LLM Adaptations
Bartłomiej Marek ⋅ Vincent Hanke ⋅ Xun Wang ⋅ Michael Backes ⋅ Adam Dziedzic ⋅ Franziska Boenisch
Integrating Object Detection Modality into Visual Language Model for Enhanced Autonomous Driving Agent
Linfeng He ⋅ Yiming Sun ⋅ Sihao Wu ⋅ Jiaxu Liu ⋅ Xiaowei Huang
Controllable Generation via Locally Constrained Resampling
Kareem Ahmed ⋅ Kai-Wei Chang ⋅ Guy Van den Broeck
Controllable Generation via Locally Constrained Resampling
Kareem Ahmed ⋅ Kai-Wei Chang ⋅ Guy Van den Broeck
The Impact of Inference Acceleration Strategies on Bias of Large Language Models
Elisabeth Kirsten ⋅ Ivan Habernal ⋅ Vedant Nanda ⋅ Muhammad Bilal Zafar
AnyPrefer: An Automatic Framework for Preference Data Synthesis
Yiyang Zhou ⋅ Zhaoyang Wang ⋅ Tianle Wang ⋅ Shangyu Xing ⋅ Peng Xia ⋅ Bo Li ⋅ Kaiyuan Zheng ⋅ Zijian Zhang ⋅ Zhaorun Chen ⋅ Wenhao Zheng ⋅ Xuchao Zhang ⋅ Chetan Bansal ⋅ Weitong Zhang ⋅ Ying Wei ⋅ Mohit Bansal ⋅ Huaxiu Yao
Steering Without Side Effects: Improving Post-Deployment Control of Language Models
Asa Cooper Stickland ⋅ Aleksandr Lyzhov ⋅ Jacob Pfau ⋅ Salsabila Mahdi ⋅ Samuel Bowman
Safe and Sound: Evaluating Language Models for Bias Mitigation and Understanding
Shaina Raza ⋅ Deval Pandya ⋅ Shardul ghuge ⋅ Nifemi
Investigating Implicit Bias in Large Language Models: A Large-Scale Study of Over 50 LLMs
Divyanshu Kumar ⋅ Umang Jain ⋅ Sahil Agarwal ⋅ Prashanth Harshangi
Self-Preference Bias in LLM-as-a-Judge
Koki Wataoka ⋅ Tsubasa Takahashi ⋅ Ryokan Ri
LLM Improvement for Jailbreak Defense: Analysis Through the Lens of Over-Refusal
Swetasudha Panda ⋅ Naveen Jafer Nizar ⋅ Michael Wick
Lexically-constrained automated prompt augmentation: A case study using adversarial T2I data
Jessica Quaye ⋅ Alicia Parrish ⋅ Oana Inel ⋅ Minsuk Kahng ⋅ Charvi Rastogi ⋅ Hannah Rose Kirk ⋅ Jess Tsang ⋅ Nathan Clement ⋅ Rafael Mosquera-Gomez ⋅ Juan Ciro ⋅ Vijay Janapa Reddi ⋅ Lora Aroyo
GenAudit: Fixing Factual Errors in Language Model Outputs with Evidence
Kundan Krishna ⋅ Sanjana Ramprasad ⋅ Prakhar Gupta ⋅ Byron Wallace ⋅ Zachary Lipton ⋅ Jeffrey Bigham
The Structural Safety Generalization Problem
Tom Gibbs ⋅ Julius Broomfield ⋅ George Ingebretsen ⋅ Ethan Kosak-Hine ⋅ Tia Nasir ⋅ Jason Zhang ⋅ Reihaneh Iranmanesh ⋅ Sara Pieri ⋅ Reihaneh Rabbany ⋅ Kellin Pelrine
Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
Chongyu Fan ⋅ Jiancheng Liu ⋅ Licong Lin ⋅ Jinghan Jia ⋅ Ruiqi Zhang ⋅ Song Mei ⋅ Sijia Liu
Debiasing Large Vision-Language Models by Ablating Protected Attribute Representations
neale ratzlaff ⋅ Matthew Olson ⋅ Musashi Hinck ⋅ Shao-Yen Tseng ⋅ VASUDEV LAL ⋅ Phillip Howard
GRE Score: Generative Risk Evaluation for Large Language Models
ZAITANG LI ⋅ Mohamed Mouhajir ⋅ Pin-Yu Chen ⋅ Tsung-Yi Ho
Identifying and Addressing Delusions for Target-Directed Decision Making
Mingde Zhao ⋅ Tristan Sylvain ⋅ Doina Precup ⋅ Yoshua Bengio
Cream: Consistency Regularized Self-Rewarding Language Models
Zhaoyang Wang ⋅ Weilei He ⋅ Zhiyuan Liang ⋅ Xuchao Zhang ⋅ Chetan Bansal ⋅ Ying Wei ⋅ Weitong Zhang ⋅ Huaxiu Yao
Fine-Tuning Large Language Models to Appropriately Abstain with Semantic Entropy
Benedict Aaron Tjandra ⋅ Muhammed Razzak ⋅ Jannik Kossen ⋅ Yarin Gal
Epistemic Integrity in Large Language Models
Bijean Ghafouri ⋅ Shahrad Mohammadzadeh ⋅ James Zhou ⋅ Pratheeksha Nair ⋅ Jacob-Junqi Tian ⋅ Mayank Goel ⋅ Reihaneh Rabbany ⋅ Jean-François Godbout ⋅ Kellin Pelrine
Differentially Private Sequential Data Synthesis with Structured State Space Models and Diffusion Models
Tomoya Matsumoto ⋅ Takayuki Miura ⋅ Toshiki Shibahara ⋅ Masanobu Kii ⋅ Kazuki Iwahana ⋅ Osamu Saisho ⋅ Shingo OKAMURA
Do LLMs estimate uncertainty well in instruction-following?
Juyeon Heo ⋅ Miao Xiong ⋅ Christina Heinze-Deml ⋅ Jaya Narain
Concept Unlearning for Large Language Models
Tomoya Yamashita ⋅ Takayuki Miura ⋅ Yuuki Yamanaka ⋅ Toshiki Shibahara ⋅ Masanori Yamada
Mitigating Hallucinations in LVLMs via Summary-Guided Decoding
Kyungmin Min ⋅ Minbeom Kim ⋅ Kang-il Lee ⋅ Dongryeol Lee ⋅ Kyomin Jung
DiffTextPure: Defending Large Language Models with Diffusion Purifiers
Huanran Chen ⋅ Ziruo Wang ⋅ Yihan Yang ⋅ Shuo Zhang ⋅ Zeming Wei ⋅ Fusheng Jin ⋅ Yinpeng Dong
Can Generative AI Solve Your In-Context Learning Problem? A Martingale Perspective
Andrew Jesson ⋅ Nicolas Beltran Velez ⋅ David Blei
On the Protocol for Evaluating Uncertainty in Generative Question-Answering Tasks
Andrea Santilli ⋅ Miao Xiong ⋅ Michael Kirchhof ⋅ Pau Rodriguez ⋅ Federico Danieli ⋅ Xavier Suau ⋅ Luca Zappella ⋅ Sinead Williamson ⋅ Adam Golinski
Pruning for Robust Concept Erasing in Diffusion Models
Tianyun Yang ⋅ Ziniu Li ⋅ Juan Cao ⋅ Chang Xu
Concept Denoising Score Matching for Responsible Text-to-Image Generation
Silpa Vadakkeeveetil Sreelatha ⋅ Sauradip Nag ⋅ Serge Belongie ⋅ Muhammad Awais ⋅ Anjan Dutta
Applying Sparse Autoencoders to Unlearn Knowledge in Language Models
Eoin Farrell ⋅ Yeu-Tong Lau ⋅ Arthur Conmy
Can Knowledge Editing Really Correct Hallucinations?
Baixiang Huang ⋅ Canyu Chen ⋅ Xiongxiao Xu ⋅ Ali Payani ⋅ Kai Shu
Imitation guided Automated Red Teaming
Desik Rengarajan ⋅ Sajad Mousavi ⋅ Ashwin Ramesh Babu ⋅ Vineet Gundecha ⋅ Avisek Naug ⋅ Sahand Ghorbanpour ⋅ Antonio Guillen-Perez ⋅ Ricardo Luna Gutierrez ⋅ Soumyendu Sarkar
Improving LLM Group Fairness on Tabular Data via In-Context Learning
Valeriia Cherepanova ⋅ Chia-Jung Lee ⋅ Nil-Jana Akpinar ⋅ Riccardo Fogliato ⋅ Martin Bertran ⋅ Michael Kearns ⋅ James Zou
Is Your Paper Being Reviewed by an LLM? Investigating AI Text Detectability in Peer Review
Sungduk Yu ⋅ Man Luo ⋅ Avinash Madasu ⋅ VASUDEV LAL ⋅ Phillip Howard
Can Editing LLMs Inject Harm?
Canyu Chen ⋅ Baixiang Huang ⋅ Zekun Li ⋅ Zhaorun Chen ⋅ Shiyang Lai ⋅ Xiongxiao Xu ⋅ Jia-Chen Gu ⋅ Jindong Gu ⋅ Huaxiu Yao ⋅ Chaowei Xiao ⋅ Xifeng Yan ⋅ William Yang Wang ⋅ Philip Torr ⋅ Dawn Song ⋅ Kai Shu
Targeted Unlearning with Single Layer Unlearning Gradient
Zikui Cai ⋅ Yaoteng Tan ⋅ M. Salman Asif
Stronger Universal and Transfer Attacks by Suppressing Refusals
David Huang ⋅ Avidan Shah ⋅ Alexandre Araujo ⋅ David Wagner ⋅ Chawin Sitawarin
Weak-to-Strong Confidence Prediction
Yukai Yang ⋅ Tracy Zhu ⋅ Marco Morucci ⋅ Tim G. J. Rudner
Fair Image Generation from Pre-trained Models by Probabilistic Modeling
Mahdi Ahmadi ⋅ John Leland ⋅ Agneet Chatterjee ⋅ YooJung Choi
Differentially Private Attention Computation
Yeqi Gao ⋅ Zhao Song ⋅ Xin Yang ⋅ Yufa Zhou
Has My System Prompt Been Used? Large Language Model Prompt Membership Inference
Roman Levin ⋅ Valeriia Cherepanova ⋅ Abhimanyu Hans ⋅ Avi Schwarzschild ⋅ Tom Goldstein
Red Teaming Language-Conditioned Robot Models via Vision Language Models
Sathwik Karnik ⋅ Zhang-Wei Hong ⋅ NISHANT ABHANGI ⋅ Yen-Chen Lin ⋅ Tsun-Hsuan Johnson Wang ⋅ Pulkit Agrawal
Pre-Training Multimodal Hallucination Detectors with Corrupted Grounding Data
Spencer Whitehead ⋅ Jacob Phillips ⋅ Sean Hendryx
Privacy Protection in Personalized Diffusion Models via Targeted Cross-Attention Adversarial Attack
Xide Xu ⋅ Muhammad Atif Butt ⋅ Sandesh Kamath ⋅ Bogdan Raducanu
DeepInception: Hypnotize Large Language Model to Be Jailbreaker
Xuan Li ⋅ Zhanke Zhou ⋅ Jianing Zhu ⋅ Jiangchao Yao ⋅ Tongliang Liu ⋅ Bo Han
HEARTS: A Holistic Framework for Explainable, Sustainable and Robust Text Stereotype Detection
Theo King ⋅ Zekun Wu ⋅ Adriano Koshiyama ⋅ Emre Kazim ⋅ Philip Treleaven
Testing the Limits of Jailbreaking with the Purple Problem
Taeyoun Kim ⋅ Suhas Kotha ⋅ Aditi Raghunathan
How to Determine the Preferred Image Distribution of a Black-Box Vision-Language Model?
Saeid Asgari ⋅ Joseph G Lambourne ⋅ Alana Mongkhounsavath
Adversarial Prompt Evaluation: Systematic Benchmarking of Guardrails Against Prompt Input Attacks on LLMs
Giulio Zizzo ⋅ Giandomenico Cornacchia ⋅ Kieran Fraser ⋅ Muhammad Zaid Hameed ⋅ Ambrish Rawat ⋅ Beat Buesser ⋅ Mark Purcell ⋅ Pin-Yu Chen ⋅ Prasanna Sattigeri ⋅ Kush Varshney
Adversarial Prompt Evaluation: Systematic Benchmarking of Guardrails Against Prompt Input Attacks on LLMs
Giulio Zizzo ⋅ Giandomenico Cornacchia ⋅ Kieran Fraser ⋅ Muhammad Zaid Hameed ⋅ Ambrish Rawat ⋅ Beat Buesser ⋅ Mark Purcell ⋅ Pin-Yu Chen ⋅ Prasanna Sattigeri ⋅ Kush Varshney
PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models
Michael-Andrei Panaitescu-Liess ⋅ Pankayaraj Pathmanathan ⋅ Yigitcan Kaya ⋅ Zora Che ⋅ Bang An ⋅ Sicheng Zhu ⋅ Aakriti Agrawal ⋅ Furong Huang
Hallucination Detox: Sensitive Neuron Dropout (SeND) for Large Language Model Training
Shahrad Mohammadzadeh ⋅ Juan D. Guerra ⋅ Marco Bonizzato ⋅ Reihaneh Rabbany ⋅ Golnoosh Farnadi
Addressing Uncertainty in LLMs to Enhance Reliability in Generative AI
Ramneet Kaur ⋅ Colin Samplawski ⋅ Adam Cobb ⋅ Anirban Roy ⋅ Brian Matejek ⋅ Manoj Acharya ⋅ Daniel Elenius ⋅ Alexander Berenbeim ⋅ John Pavlik ⋅ Nathaniel Bastian ⋅ Susmit Jha
Jogging the Memory of Unlearned LLMs Through Targeted Relearning Attacks
Shengyuan Hu ⋅ Yiwei Fu ⋅ Steven Wu ⋅ Virginia Smith
A Closer Look at System Message Robustness
Norman Mu ⋅ Jonathan Lu ⋅ Michael Lavery ⋅ David Wagner
The effect of fine-tuning on language model toxicity
Will Hawkins ⋅ Brent Mittelstadt ⋅ Chris Russell
The effect of fine-tuning on language model toxicity
Will Hawkins ⋅ Brent Mittelstadt ⋅ Chris Russell
Auto-Enhance: Towards a Meta-Benchmark to Evaluate AI Agents' Ability to Improve Other Agents
Samuel Brown ⋅ Basil Labib ⋅ Codruta Lugoj ⋅ Sai Sasank Y
Model Manipulation Attacks Enable More Rigorous Evaluations of LLM Unlearning
Zora Che ⋅ Stephen Casper ⋅ Anirudh Satheesh ⋅ Rohit Gandikota ⋅ Domenic Rosati ⋅ Stewart Slocum ⋅ Lev McKinney ⋅ Zichu Wu ⋅ Zikui Cai ⋅ Bilal Chughtai ⋅ Furong Huang ⋅ Dylan Hadfield-Menell
Large Language Model Benchmarks Do Not Test Reliability
Joshua Vendrow ⋅ Edward Vendrow ⋅ Sara Beery ⋅ Aleksander Madry
EchoQA: A Large Collection of Instruction Tuning Data for Echocardiogram Reports
Lama Moukheiber ⋅ Mira Moukheiber ⋅ Dana Moukheiber ⋅ Jae-Woo Ju ⋅ Hyung-Chul Lee
On Calibration of LLM-based Guard Models for Reliable Content Moderation
Hongfu Liu ⋅ Hengguan Huang ⋅ Hao Wang ⋅ Xiangming Gu ⋅ Ye Wang
On Calibration of LLM-based Guard Models for Reliable Content Moderation
Hongfu Liu ⋅ Hengguan Huang ⋅ Hao Wang ⋅ Xiangming Gu ⋅ Ye Wang
AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
Yifan Zeng ⋅ Yiran Wu ⋅ Xiao Zhang ⋅ Huazheng Wang ⋅ Qingyun Wu
How Many Van Goghs Does It Take to Van Gogh? Finding the Imitation Threshold
Sahil Verma ⋅ Royi Rassin ⋅ Arnav Das ⋅ Gantavya Bhatt ⋅ Preethi Seshadri ⋅ Chirag Shah ⋅ Jeff A Bilmes ⋅ Hannaneh Hajishirzi ⋅ Yanai Elazar
Applying Refusal-Vector Ablation to Llama 3.1 70B Agents
Simon Lermen ⋅ Mateusz Dziemian ⋅ Govind Pimpale
Language Models Can Articulate Their Implicit Goals
Jan Betley ⋅ Xuchan Bao ⋅ Martín Soto ⋅ Anna Sztyber-Betley ⋅ James Chua ⋅ Owain Evans
Energy-Based Conceptual Diffusion Model
Yi Qin ⋅ Xinyue Xu ⋅ Hao Wang ⋅ Xiaomeng Li
MultiVerse: Exposing Large Language Model Alignment Problems in Diverse Worlds
Xiaolong Jin ⋅ Zhuo Zhang ⋅ Guangyu Shen ⋅ Hanxi Guo ⋅ Kaiyuan Zhang ⋅ Siyuan Cheng ⋅ Xiangyu Zhang
$\textit{Who Speaks Matters}$: Analysing the Influence of the Speaker’s Ethnicity on Hate Classification
Ananya Malik ⋅ Kartik Sharma ⋅ Lynnette Hui Xian Ng ⋅ Shaily Bhatt
$\textit{Who Speaks Matters}$: Analysing the Influence of the Speaker’s Ethnicity on Hate Classification
Ananya Malik ⋅ Kartik Sharma ⋅ Lynnette Hui Xian Ng ⋅ Shaily Bhatt
Safety-Aware Fine-Tuning of Large Language Models
Hyeong Kyu Choi ⋅ Xuefeng Du ⋅ Sharon Li
Buffer Overflow in Mixture of Experts
Jamie Hayes ⋅ I Shumailov ⋅ Itay Yona
Extracting Unlearned Information from LLMs with Activation Steering
Atakan Seyitoğlu ⋅ Aleksei Kuvshinov ⋅ Leo Schwinn ⋅ Stephan Günnemann
Can Safety Fine-Tuning Be More Principled? Lessons Learned from Cybersecurity
David Williams-King ⋅ Linh Le ⋅ Adam Oberman ⋅ Yoshua Bengio
Efficient and Effective Uncertainty Quantification for LLMs
Miao Xiong ⋅ Andrea Santilli ⋅ Michael Kirchhof ⋅ Adam Golinski ⋅ Sinead Williamson
EnsemW2S: Can an Ensemble of LLMs be Leveraged to Obtain a Stronger LLM?
Aakriti Agrawal ⋅ Mucong Ding ⋅ Zora Che ⋅ Chenghao Deng ⋅ Anirudh Satheesh ⋅ John Langford ⋅ Furong Huang
MED: Exploring LLM Memorization on Encrypted Data
Panagiotis christodoulou ⋅ Giulio Zizzo ⋅ Sergio Maffeis
Towards Resource Efficient and Interpretable Bias Mitigation in Natural Language Generation
Schrasing Tong ⋅ Eliott Zemour ⋅ Rawisara Lohanimit ⋅ Lalana Kagal
NMT-Obfuscator Attack: Ignore a sentence in translation with only one word
Sahar Sadrizadeh ⋅ César Descalzo ⋅ Ljiljana Dolamic ⋅ Pascal Frossard
A Probabilistic Generative Method for Safe Physical System Control Problems
Peiyan Hu ⋅ Xiaowei Qian ⋅ Wenhao Deng ⋅ Rui Wang ⋅ Haodong Feng ⋅ Ruiqi Feng ⋅ Tao Zhang ⋅ Long Wei ⋅ Yue Wang ⋅ Zhi-Ming Ma ⋅ Tailin Wu
MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models
Peng Xia ⋅ Kangyu Zhu ⋅ Haoran Li ⋅ Tianze Wang ⋅ Weijia Shi ⋅ Sheng Wang ⋅ Linjun Zhang ⋅ James Zou ⋅ Huaxiu Yao
PopAlign: Population-Level Alignment for Fair Text-to-Image Generation
Shufan Li ⋅ Harkanwar Singh ⋅ Aditya Grover
Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack
Leo McKee-Reid ⋅ Christoph Sträter ⋅ Maria Martinez ⋅ Joe Needham ⋅ Mikita Balesni
SCIURus: Shared Circuits for Interpretable Uncertainty Representations in Language Models
Carter Teplica ⋅ Yixin Liu ⋅ Arman Cohan ⋅ Tim G. J. Rudner
CoS: Enhancing Personalization and Mitigating Bias with Context Steering
Sashrika Pandey ⋅ Jerry He ⋅ Mariah Schrum ⋅ Anca Dragan
What You See Is What You Get: Entity-Aware Summarization for Reliable Sponsored Search
Xiao Liang ⋅ Xinyu Hu ⋅ Simiao Zuo ⋅ Jimi He ⋅ Yu Wang ⋅ Victor Dong ⋅ Yeyun Gong ⋅ Kushal Dave ⋅ Yi Liu ⋅ Qiang Lou ⋅ Shao-Lun Huang ⋅ Jian Jiao
How new data pollutes LLM knowledge and how to dilute it
Chen Sun ⋅ Renat Aksitov ⋅ Andrey Zhmoginov ⋅ Nolan Miller ⋅ Max Vladymyrov ⋅ Ulrich Rueckert ⋅ Been Kim ⋅ Mark Sandler
Mix Data or Merge Models? Optimizing for Performance and Safety in Multilingual Contexts
Aakanksha ⋅ Arash Ahmadian ⋅ Seraphina Goldfarb-Tarrant ⋅ Beyza Ermis ⋅ Marzieh Fadaee ⋅ Sara Hooker
Simulation System Towards Solving Societal-Scale Manipulation
Maximilian Puelma Touzel ⋅ Sneheel Sarangi ⋅ Austin Welch ⋅ Gayatri K ⋅ Dan Zhao ⋅ Zachary Yang ⋅ Hao Yu ⋅ Tom Gibbs ⋅ Ethan Kosak-Hine ⋅ Andreea Musulan ⋅ Camille Thibault ⋅ Busra Gurbuz ⋅ Reihaneh Rabbany ⋅ Jean-François Godbout ⋅ Kellin Pelrine
Red Teaming: Everything Everywhere All at Once
Alexandra Chouldechova ⋅ A. Feder Cooper ⋅ Abhinav Palia ⋅ Dan Vann ⋅ Chad Atalla ⋅ Hannah Washington ⋅ Emily Sheng ⋅ Hanna Wallach
Inference, Fast and Slow: Reinterpreting VAEs for OOD Detection
Sicong (Sheldon) Huang ⋅ Jiawei He ⋅ Kry Yik Chau Lui
The Empirical Impact of Data Sanitization on Language Models
Anwesan Pal ⋅ Radhika Bhargava ⋅ Kyle Hinsz ⋅ Jacques Esterhuizen ⋅ Sudipta Bhattacharya
IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization
Ahmed Frikha ⋅ Nassim Walha ⋅ Krishna Nakka ⋅ Ricardo Mendes ⋅ Xue Jiang ⋅ Xuebing Zhou
Quantifying Likeness: A Simple Machine Learning Approach to Identifying Copyright Infringement in (AI-Generated) Artwork
Michaela Drouillard ⋅ Ryan Spencer ⋅ Nikée Nantambu-Allen ⋅ Tegan Maharaj
An Undetectable Watermark for Generative Image Models
Sam Gunn ⋅ Xuandong Zhao ⋅ Dawn Song
RLHS: Mitigating Misalignment in RLHF with Hindsight Simulation
Kaiqu Liang ⋅ Haimin Hu ⋅ Ryan Liu ⋅ Tom Griffiths ⋅ Jaime Fisac
Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates
Xiaosen Zheng ⋅ Tianyu Pang ⋅ Chao Du ⋅ Qian Liu ⋅ Jing Jiang ⋅ Min Lin
Differential Privacy of Cross-Attention with Provable Guarantee
Yingyu Liang ⋅ Zhenmei Shi ⋅ Zhao Song ⋅ Yufa Zhou
Smoothed Embeddings for Robust Language Models
Ryo Hase ⋅ Rafi Rashid ⋅ Ashley Lewis ⋅ Jing Liu ⋅ Toshiaki Koike-Akino ⋅ Kieran Parsons ⋅ Ye Wang
What do we learn from inverting CLIP models?
Hamid Kazemi ⋅ Atoosa Chegini ⋅ Jonas Geiping ⋅ Soheil Feizi ⋅ Tom Goldstein
Does Refusal Training in LLMs Generalize to the Past Tense?
Maksym Andriushchenko ⋅ Nicolas Flammarion
Does Refusal Training in LLMs Generalize to the Past Tense?
Maksym Andriushchenko ⋅ Nicolas Flammarion
LLM Targeted Underperformance Disproportionately Impacts Vulnerable Users
Elinor Poole-Dayan ⋅ Deb Roy ⋅ Jad Kabbara
AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment
Pankayaraj Pathmanathan ⋅ Udari Sehwag ⋅ Michael-Andrei Panaitescu-Liess ⋅ Furong Huang
Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy
Tong Wu ⋅ Shujian Zhang ⋅ Kaiqiang Song ⋅ Silei Xu ⋅ Sanqiang Zhao ⋅ Ravi Agrawal ⋅ Sathish Indurthi ⋅ Chong Xiang ⋅ Prateek Mittal ⋅ Wenxuan Zhou
INVESTIGATING ANNOTATOR BIAS IN LARGE LANGUAGE MODELS FOR HATE SPEECH DETECTION
Amit Das ⋅ Zheng Zhang ⋅ Md. Najib Hasan ⋅ Souvika Sarkar ⋅ Fatemeh Jamshidi ⋅ Tathagata Bhattacharya ⋅ Mostafa Rahgouy ⋅ Nilanjana Raychawdhary ⋅ Dongji Feng ⋅ Vinija Jain ⋅ Aman Chadha ⋅ Mary Sandage ⋅ Lauramarie Pope ⋅ Gerry Dozier ⋅ Cheryl Seals
Towards Inference-time Category-wise Safety Steering for Large Language Models
Amrita Bhattacharjee ⋅ Shaona Ghosh ⋅ Traian Rebedea ⋅ Christopher Parisien
Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs
Yohan Mathew ⋅ Ollie Matthews ⋅ Robert McCarthy ⋅ Joan Velja ⋅ Christian Schroeder de Witt ⋅ Dylan Cope ⋅ Nandi Schoots
INTERPRETABILITY OF LLM DECEPTION: UNIVERSAL MOTIF
Wannan Yang ⋅ Chen Sun ⋅ Gyorgy Buzsaki
Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning
Somnath Basu Roy Chowdhury ⋅ Krzysztof M Choromanski ⋅ Arijit Sehanobish ⋅ Kumar Avinava Dubey ⋅ Snigdha Chaturvedi
Exploring Memorization and Copyright Violation in Frontier LLMs: A Study of the New York Times v. OpenAI 2023 Lawsuit
Joshua Freeman ⋅ Chloe Rippe ⋅ Edoardo Debenedetti ⋅ Maksym Andriushchenko
Is What You Ask For What You Get? Investigating Concept Associations in Text-to-Image Models
Salma Abdel Magid ⋅ Weiwei Pan ⋅ Simon Warchol ⋅ Grace Guo ⋅ Junsik Kim ⋅ Wanhua Li ⋅ Mahia Rahman ⋅ Hanspeter Pfister
How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompt
Yusu Qian ⋅ Haotian Zhang ⋅ Yinfei Yang ⋅ Zhe Gan
Variational Diffusion Unlearning: a variational inference framework for unlearning in diffusion models
Subhodip Panda ⋅ M S Varun ⋅ Shreyans Jain ⋅ Sarthak Kumar Maharana ⋅ Prathosh AP
Dynamic Negative Guidance of Diffusion Models: Towards Immediate Content Removal
Felix Koulischer ⋅ Johannes Deleu ⋅ Gabriel Raya ⋅ Thomas Demeester ⋅ Luca Ambrogioni
Gaussian Splatting Under Attack: Investigating Adversarial Noise in 3D Objects
Abdurrahman Zeybey ⋅ Mehmet Ergezer ⋅ Tommy Nguyen
Insights on Disagreement Patterns in Multimodal Safety Perception across Diverse Rater Groups
Charvi Rastogi ⋅ Tian Huey Teh ⋅ Pushkar Mishra ⋅ Roma Patel ⋅ Zoe Ashwood ⋅ Aida Mostafazadeh Davani ⋅ Mark Díaz ⋅ Michela Paganini ⋅ Alicia Parrish ⋅ Ding Wang ⋅ Vinodkumar Prabhakaran ⋅ Lora Aroyo ⋅ Verena Rieser
Rule-Guided Language Model Alignment for Text Generation Management in Industrial Use Cases
Shunichi Akatsuka ⋅ Aman Kumar ⋅ Xian Yeow Lee ⋅ Lasitha Vidyaratne ⋅ Dipanjan Ghosh ⋅ Ahmed Farahat
ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates
Fengqing Jiang ⋅ Zhangchen Xu ⋅ Luyao Niu ⋅ Bill Yuchen Lin ⋅ Radha Poovendran
Efficiently Identifying Watermarked Segments in Mixed-Source Texts
Xuandong Zhao ⋅ Chenwen Liao ⋅ Yu-Xiang Wang ⋅ Lei Li
Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting
Fuqiang Liu ⋅ Sicong Jiang ⋅ Luis Miranda-Moreno ⋅ Seongjin Choi ⋅ Lijun Sun
SolidMark: Evaluating Image Memorization in Generative Models
Nicky Kriplani ⋅ Minh Pham ⋅ Gowthami Somepalli ⋅ Chinmay Hegde ⋅ Niv Cohen
Self-Supervised Bisimulation Action Chunk Representation for Efficient RL
Lei Shi ⋅ Jianye Hao ⋅ Hongyao Tang ⋅ Zibin Dong ⋅ YAN ZHENG
Anchored Optimization and Contrastive Revisions: Addressing Reward Hacking in Alignment
Karel Doosterlinck ⋅ Winnie Xu ⋅ Chris Develder ⋅ Thomas Demeester ⋅ Amanpreet Singh ⋅ Christopher Potts ⋅ Douwe Kiela ⋅ Shikib Mehri
Interactive Semantic Interventions for VLMs: A Human-in-the-Loop Investigation of VLM Failure
Lukas Klein ⋅ Kenza Amara ⋅ Carsten Lüth ⋅ Hendrik Strobelt ⋅ Mennatallah El-Assady ⋅ Paul Jaeger
Can LLMs Verify Arabic Claims? Evaluating the Arabic Fact-Checking Abilities of Multilingual LLMs
Aryan Singhal ⋅ Ayushman Gupta ⋅ Ryan L Li ⋅ Evan Duan ⋅ Thomas Law ⋅ Veekshith Rao
MMLU-Pro+: Evaluating Higher-Order Reasoning and Shortcut Learning in LLMs
Saeid Asgari ⋅ Aliasghar Khani ⋅ Amir Khasahmadi
Unlearning in- vs. out-of-distribution data in LLMs under gradient-based methods
Teodora Baluta ⋅ Gintare Karolina Dziugaite ⋅ Pascal Lamblin ⋅ Fabian Pedregosa ⋅ Danny Tarlow
A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage
Rui Xin ⋅ Niloofar Mireshghallah ⋅ Stella Li ⋅ Michael Duan ⋅ Hyunwoo Kim ⋅ Yejin Choi ⋅ Yulia Tsvetkov ⋅ Sewoong Oh ⋅ Pang Wei Koh
Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity
Rheeya Uppaal ⋅ Apratim Dey ⋅ Yiting He ⋅ Yiqiao Zhong ⋅ Junjie Hu
LoReUn: Data Itself Implicitly Provides Cues to Improve Machine Unlearning
Xiang Li ⋅ Qianli Shen ⋅ Haonan Wang ⋅ Kenji Kawaguchi
CPSample: Classifier Protected Sampling for Guarding Training Data During Diffusion
Joshua Kazdan ⋅ Hao Sun ⋅ Jiaqi Han ⋅ Felix Petersen ⋅ Frederick Vu ⋅ Stefano Ermon
Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance
Linxi Zhao ⋅ Yihe Deng ⋅ Weitong Zhang ⋅ Quanquan Gu
Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?
Sravanti Addepalli ⋅ Yerram Varun ⋅ Arun Suggala ⋅ Karthikeyan Shanmugam ⋅ Prateek Jain
AEGIS2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails
Shaona Ghosh ⋅ Prasoon Varshney ⋅ Makesh Narsimhan Sreedhar ⋅ Aishwarya Padmakumar ⋅ Traian Rebedea ⋅ Jibin Varghese ⋅ Christopher Parisien