AI Safety

Extreme Miscalibration and the Illusion of Adversarial Robustness ACL 2024 Fair Secretaries with Unfair Predictions NeurIPS 2024 Fake Alignment: Are LLMs Really Aligned Well? NAACL 2024 Fast Adversarial Attacks on Language Models In One GPU Minute ICML 2024 Fast Best-of-N Decoding via Speculative Rejection NeurIPS 2024 Federated Learning with Extremely Noisy Clients via Negative Distillation AAAI 2024 Feedback Loops With Language Models Drive In-Context Reward Hacking ICML 2024 FESSNC: Fast Exponentially Stable and Safe Neural Controller ICML 2024 Fight Back Against Jailbreaking via Prompt Adversarial Tuning NeurIPS 2024 Find the Lady: Permutation and Re-synchronization of Deep Neural Networks AAAI 2024 Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! ICLR 2024 Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clients NeurIPS 2024 Fishing for Magikarp: Automatically Detecting Under-trained Tokens in Large Language Models EMNLP 2024 Fixing Overconfidence in Dynamic Neural Networks WACV 2024 Flames: Benchmarking Value Alignment of LLMs in Chinese NAACL 2024 Flatness-aware Sequential Learning Generates Resilient Backdoors ECCV 2024 FLIRT: Feedback Loop In-context Red Teaming EMNLP 2024 Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training CVPR 2024 FOFO: A Benchmark to Evaluate LLMs’ Format-Following Capability ACL 2024 Fooling Polarization-Based Vision using Locally Controllable Polarizing Projection CVPR 2024 Formalisation and Evaluation of Properties for Consequentialist Machine Ethics IJCAI 2024 Formal Verification of Unknown Stochastic Systems via Non-parametric Estimation AISTATS 2024 Fostering Trustworthiness in Machine Learning Algorithms AAAI 2024 From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models EMNLP 2024 From LLMs to MLLMs: Exploring the Landscape of Multimodal Jailbreaking EMNLP 2024