SOTAVerified

Safety Alignment

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 251–288 of 288 papers

TitleStatusHype
Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy OptimizationCode0
One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMsCode0
SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity GuidanceCode0
SeqAR: Jailbreak LLMs with Sequential Auto-Generated CharactersCode0
Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks SafetyCode0
Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety AlignmentCode0
DuFFin: A Dual-Level Fingerprinting Framework for LLMs IP ProtectionCode0
Monitoring Decomposition Attacks in LLMs with Lightweight Sequential MonitorsCode0
Mitigating Safety Fallback in Editing-based Backdoor Injection on LLMsCode0
Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language ModelsCode0
DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language ModelsCode0
Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMsCode0
Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning ModelsCode0
Mitigating Fine-tuning Risks in LLMs via Safety-Aware Probing OptimizationCode0
Don't Command, Cultivate: An Exploratory Study of System-2 AlignmentCode0
A Common Pitfall of Margin-based Language Model Alignment: Gradient EntanglementCode0
BiasJailbreak:Analyzing Ethical Biases and Jailbreak Vulnerabilities in Large Language ModelsCode0
Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context AttackCode0
LLM Safety Alignment is Divergence Estimation in DisguiseCode0
Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety AlignmentCode0
Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacksCode0
StructTransform: A Scalable Attack Surface for Safety-Aligned Large Language ModelsCode0
Keep Security! Benchmarking Security Policy Preservation in Large Language Model Contexts Against Indirect Attacks in Question AnsweringCode0
Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal ModelsCode0
Iterative Self-Tuning LLMs for Enhanced Jailbreaking CapabilitiesCode0
How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their VulnerabilitiesCode0
DiaBlo: Diagonal Blocks Are Sufficient For FinetuningCode0
VSCBench: Bridging the Gap in Vision-Language Model Safety CalibrationCode0
SafeWorld: Geo-Diverse Safety AlignmentCode0
Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language ModelsCode0
Unlocking Adversarial Suffix Optimization Without Affirmative Phrases: Efficient Black-box Jailbreaking via LLM as OptimizerCode0
Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual UnderstandingCode0
SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task LinkageCode0
SAGE: A Generic Framework for LLM Safety EvaluationCode0
SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic EmbeddingsCode0
The Better Angels of Machine Personality: How Personality Relates to LLM SafetyCode0
TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data SynthesisCode0
Can a large language model be a gaslighter?Code0
Show:102550
← PrevPage 6 of 6Next →

No leaderboard results yet.