conftrace_
← Core AI
Artificial Intelligence › Core AI ›

AI Safety

3,026 papers

Papers per year

5
111
1031
'15
'20
'25

Papers

ReMoDetect: Reward Models Recognize Aligned LLM's Generations NIPS 2024
LT-Defense: Searching-free Backdoor Defense via Exploiting the Long-tailed Effect NIPS 2024
Fair Secretaries with Unfair Predictions NIPS 2024
Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models NIPS 2024
BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment NIPS 2024
HonestLLM: Toward an Honest and Helpful Large Language Model NIPS 2024
MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models NIPS 2024
WildGuard: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs NIPS 2024
Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space NIPS 2024
I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token NIPS 2024
Measuring Goal-Directedness NIPS 2024
Representation Noising: A Defence Mechanism Against Harmful Finetuning NIPS 2024
Towards Safe Concept Transfer of Multi-Modal Diffusion via Causal Representation Editing NIPS 2024
ProgressGym: Alignment with a Millennium of Moral Progress NIPS 2024
Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification NIPS 2024
Segmenting Watermarked Texts From Language Models NIPS 2024
SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset NIPS 2024
Watermarking Makes Language Models Radioactive NIPS 2024
Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models NIPS 2024
Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization NIPS 2024
If You Want to Be Robust, Be Wary of Initialization NIPS 2024
Data Free Backdoor Attacks NIPS 2024
When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search NIPS 2024
A theoretical case-study of Scalable Oversight in Hierarchical Reinforcement Learning NIPS 2024
Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data NIPS 2024