ICML 2024 Workshop NextGenAISafety Submissions

Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
Anay Mehrotra, Manolis Zampetakis, Paul Kassianik, Blaine Nelson, Hyrum S Anderson, Yaron Singer, Amin Karbasi
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Chained Tuning Leads to Biased Forgetting
Megan Ung, Alicia Yi Sun, Samuel Bell, Levent Sagun, Adina Williams
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Safer Reinforcement Learning by Going Off-policy: a Benchmark
Igor Kuznetsov
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Generated Audio Detectors are Not Robust in Real-World Conditions
Soumya Shaw, Ben Nassi, Lea Schönherr
- Published: 28 Jun 2024, Last Modified: 26 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Bias Transmission in Large Language Models: Evidence from Gender-Occupation Bias in GPT-4
Kirsten Morehouse, Weiwei Pan, Juan Manuel Contreras, Mahzarin R. Banaji
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Enhancing Concept-based Learning with Logic
Deepika Vemuri, Gautham Bellamkonda, Vineeth N. Balasubramanian
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Medical Unlearnable Examples: Securing Medical Data from Unauthorized Training via Sparsity-Aware Local Masking
Weixiang Sun, Yixin Liu, Zhiling Yan, Kaidi Xu, Lichao Sun
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Can Language Models Safeguard Themselves, Instantly and For Free?
Dyah Adila, Changho Shin, Yijing Zhang, Frederic Sala
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Robustness Analysis of AI Models in Critical Energy Systems
Pantelis Dogoulis, matthieu jimenez, Maxime Cordy, Salah GHAMIZI, YVES LE TRAON
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Is My Data Safe? Predicting Instance-Level Membership Inference Success for White-box and Black-box Attacks
Tobias Leemann, Bardh Prenkaj, Gjergji Kasneci
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Using Large Language Models for Humanitarian Frontline Negotiation: Opportunities and Considerations
Zilin Ma, Susannah Cheng Su, Nathan Zhao, Linn Bieske, Blake Bullwinkel, Yanyi Zhang, Jinglun Gao, Gekai Liao, Siyao Li, Ziqing Luo, Boxiang Wang, Zihan Wen, Yanrui Yang, Claude Bruderlein, Weiwei Pan
- Published: 28 Jun 2024, Last Modified: 29 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
On the Calibration of Conditional-Value-at-Risk
Rajeev Verma, Volker Fischer, Eric Nalisnick
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
PrimeGuard: Safe and Helpful LLMs through Tuning-Free Routing
Blazej Manczak, Eric Lin, Eliott Zemour, Vaikkunth Mugunthan
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Decomposed evaluations of geographic disparities in text-to-image models
Abhishek Sureddy, Dishant Padalia, Nandhinee Periyakaruppan, Oindrila Saha, Adina Williams, Adriana Romero-Soriano, Megan Richards, Polina Kirichenko, Melissa Hall
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Uncovering a Culture of AI Grassroots Experimentation by Boston City Employees: Safety Risks and Mitigation
Jude Ha, Audrey Xing-Yun Chang
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Ethical-Lens: Curbing Malicious Usages of Open-Source Text-to-Image Models
Yuzhu Cai, Sheng Yin, Yuxi Wei, Chenxin Xu, Weibo Mao, Felix Juefei-Xu, Siheng Chen, Yanfeng Wang
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
FairPFN: Transformers Can do Counterfactual Fairness
Jake Robertson, Noah Hollmann, Noor Awad, Frank Hutter
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
AdaptiveBackdoor: Backdoored Language Model Agents that Detect Human Overseers
Heng Wang, Ruiqi Zhong, Jiaxin Wen, Jacob Steinhardt
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Marginal Fairness Sliced Wasserstein Barycenter
Khai Nguyen, Hai Nguyen, Nhat Ho
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
On the Robustness of Neural Networks Quantization against Data Poisoning Attacks
Yiwei Lu, Yihan Wang, Guojun Zhang, Yaoliang Yu
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
One-Shot Safety Alignment for Large Language Models via Optimal Dualization
Xinmeng Huang, Shuo Li, Edgar Dobriban, Osbert Bastani, Hamed Hassani, Dongsheng Ding
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Models That Prove Their Own Correctness
Noga Amit, Shafi Goldwasser, Orr Paradise, Guy N. Rothblum
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Exploring Scaling Trends in LLM Robustness
Nikolaus H. R. Howe, Michał Zając, Ian R. McKenzie, Oskar John Hollinsworth, Pierre-Luc Bacon, Adam Gleave
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone
Manipulating Feature Visualizations with Gradient Slingshots
Dilyara Bareeva, Marina MC Höhne, Alexander Warnecke, Lukas Pirch, Klaus Robert Muller, Konrad Rieck, Kirill Bykov
- Published: 28 Jun 2024, Last Modified: 25 Jul 2024
- NextGenAISafety 2024 Poster
- Readers: Everyone