conftrace_

model safety

101 papers

Explore in graph

Co-occurring keywords

large language model (13587) jailbreak attack (225) adversarial attack (1621) safety alignment (178) ai safety (235) adversarial learning (1595) adversarial robustness (1341) model alignment (226) language model (4599) jailbreaking attack (26)

Papers

Safeguarding Language Models via Self-Destruct Trapdoor EACL 2026
Distractor-Based Jailbreaking Attacks in Language Models and Associated Changes in Chain-of-Thought Content (Student Abstract) AAAI 2026
Towards Inclusive AI: Advancing Multilingual Large Language Models AAAI 2026
Exploiting Synergistic Cognitive Biases to Bypass Safety in LLMs AAAI 2026
Safe Vision-Language Models via Unsafe Weights Manipulation WACV 2026
A Robust Unlearning Method with Adaptive Knowledge Guidance and Memory Preservation AAAI 2026
Where to Start Alignment? Diffusion Large Language Model May Demand a Distinct Position AAAI 2026
Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks AAAI 2026
Safety in Large Reasoning Models: A Survey EMNLP 2025
Advancing Oversight Reasoning across Languages for Audit Sycophantic Behaviour via X-Agent EMNLP 2025
An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer NAACL 2025
Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time EMNLP 2025
Rescorla-Wagner Steering of LLMs for Undesired Behaviors over Disproportionate Inappropriate Context EMNLP 2025
Improving Large Language Model Safety with Contrastive Representation Learning EMNLP 2025
Role-Aware Language Models for Secure and Contextualized Access Control in Organizations AACL 2025
SURE: Safety Understanding and Reasoning Enhancement for Multimodal Large Language Models EMNLP 2025
Advancing Intelligent Software Development and Trustworthy Models Through the Synergy of Software Engineering and LLMs AAAI 2025
MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol EMNLP 2025
Speculative Safety-Aware Decoding EMNLP 2025
SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities ACL 2025
Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective COLING 2025
Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment EMNLP 2025
LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion ACL 2025
Can LLMs Rank the Harmfulness of Smaller LLMs? We are Not There Yet ACL 2025
Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update AAAI 2025