SOTAVerified

Safety Alignment

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–150 of 288 papers

TitleStatusHype
Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning—0
DiaBlo: Diagonal Blocks Are Sufficient For FinetuningCode0
BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream CamouflageCode0
Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models—0
Bootstrapping LLM Robustness for VLM Safety via Reducing the Pretraining Modality Gap—0
TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data SynthesisCode0
SafeCOMM: What about Safety Alignment in Fine-Tuned Telecom Large Language Models?—0
AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language ModelsCode0
EVOREFUSE: Evolutionary Prompt Optimization for Evaluation and Mitigation of LLM Over-Refusal to Pseudo-Malicious Instructions—0
Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack—0
OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image ModelsCode0
PoisonSwarm: Universal Harmful Information Synthesis via Model Crowdsourcing—0
SOSBENCH: Benchmarking Safety Alignment on Scientific Knowledge—0
VSCBench: Bridging the Gap in Vision-Language Model Safety CalibrationCode0
Reshaping Representation Space to Balance the Safety and Over-rejection in Large Audio Language Models—0
SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety—0
Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning ModelsCode0
Does Representation Intervention Really Identify Desired Concepts and Elicit Alignment?—0
Safety Alignment via Constrained Knowledge Unlearning—0
Alignment and Safety of Diffusion Models via Reinforcement Learning and Reward Modeling: A Survey—0
Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary—0
One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMsCode0
DuFFin: A Dual-Level Fingerprinting Framework for LLMs IP ProtectionCode0
Mitigating Fine-tuning Risks in LLMs via Safety-Aware Probing OptimizationCode0
From Evaluation to Defense: Advancing Safety in Video Large Language Models—0
CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning—0
Shape it Up! Restoring LLM Safety during Finetuning—0
Keep Security! Benchmarking Security Policy Preservation in Large Language Model Contexts Against Indirect Attacks in Question AnsweringCode0
"Haet Bhasha aur Diskrimineshun": Phonetic Perturbations in Code-Mixed Hinglish to Red-Team LLMs—0
SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment—0
sudoLLM : On Multi-role Alignment of Language Models—0
Safety Alignment Can Be Not Superficial With Explicit Safety Signals—0
SafeVid: Toward Safety Aligned Video Large Multimodal Models—0
JULI: Jailbreak Large Language Models by Self-Introspection—0
Noise Injection Systemically Degrades Large Language Model Safety Guardrails—0
CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMs—0
Analysing Safety Risks in LLMs Fine-Tuned with Pseudo-Malicious Cyber Security Data—0
FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning—0
One Trigger Token Is Enough: A Defense Strategy for Balancing Safety and Usability in Large Language Models—0
Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks SafetyCode0
Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning ModelCode0
NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models—0
SAGE: A Generic Framework for LLM Safety EvaluationCode0
What's Pulling the Strings? Evaluating Integrity and Attribution in AI Training and Inference through Concept Shift—0
AI Awareness—0
DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language ModelsCode0
aiXamine: Simplified LLM Safety and Security—0
Towards NSFW-Free Text-to-Image Generation via Safety-Constraint Direct Preference Optimization—0
Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models—0
VLMGuard-R1: Proactive Safety Alignment for VLMs via Reasoning-Driven Prompt Optimization—0
Show:102550
← PrevPage 3 of 6Next →

No leaderboard results yet.