conftrace_

harmful behavior

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (4) harmful content (2) safety risk (1) adversarial image (1) language model safety (1) persona bia (1) proximity constraint (1) demographic persona (1) security assessment (1) psychological analysis (1)

Papers

AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin AAAI 2026 ChameleonBench: Quantifying Alignment Faking in Large Language Models ACML 2025 Text-Diffusion Red-Teaming of Large Language Models: Unveiling Harmful Behaviors with Proximity Constraints AAAI 2025 Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights ACL 2025 Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast ICML 2024 Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems EMNLP 2023