← Core AI
Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

Exploiting the Shadows: Unveiling Privacy Leaks through Lower-Ranked Tokens in Large Language Models ACL 2025
Adversarial Robust Memory-Based Continual Learner ICCV 2025
Gradient-Reweighted Adversarial Camouflage for Physical Object Detection Evasion ICCV 2025
VLSBench: Unveiling Visual Leakage in Multimodal Safety ACL 2025
Are Stereotypes Leading LLMs’ Zero-Shot Stance Detection ? EMNLP 2025
Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks ICCV 2025
Towards Adversarial Robustness via Debiased High-Confidence Logit Alignment ICCV 2025
AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection ACL 2025
Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency ICCV 2025
Backdoor Mitigation by Distance-Driven Detoxification ICCV 2025
LLM as a Broken Telephone: Iterative Generation Distorts Information ACL 2025
LLMScan: Causal Scan for LLM Misbehavior Detection ICML 2025
NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning AAAI 2025
LlmFixer: Fix the Helpfulness of Defensive Large Language Models EMNLP 2025
The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas EMNLP 2025
Certified Mitigation of Worst-Case LLM Copyright Infringement EMNLP 2025
The Confidence Paradox: Can LLM Know When It’s Wrong? IJCNLP 2025
DISTIL: Data-Free Inversion of Suspicious Trojan Inputs via Latent Diffusion ICCV 2025
Biased LLMs can Influence Political Decision-Making ACL 2025
Profiling LLM’s Copyright Infringement Risks under Adversarial Persuasive Prompting EMNLP 2025
SimVBG: Simulating Individual Values by Backstory Generation EMNLP 2025
Learning to Rewrite: Generalized LLM-Generated Text Detection ACL 2025
Neutral Is Not Unbiased: Evaluating Implicit and Intersectional Identity Bias in LLMs Through Structured Narrative Scenarios EMNLP 2025
Self-adaptive Dataset Construction for Real-World Multimodal Safety Scenarios EMNLP 2025
Building Safe GenAI Applications: An End-to-End Overview of Red Teaming for Large Language Models NAACL 2025