Papers with Code 아카이브
Safety Alignment
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
TuneShield: Mitigating Toxicity in Conversational AI while Fine-tuning on Untrusted Data
Trojan Horse Prompting: Jailbreaking Conversational Multimodal Models by Forging Assistant Message
Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning
Security Assessment of DeepSeek and GPT Series Models against Jailbreak Attacks
Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs
SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification
Probing the Robustness of Large Language Models Safety to Latent Perturbations
Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
Don't Make It Up: Preserving Ignorance Awareness in LLM Fine-Tuning
Mitigating Safety Fallback in Editing-based Backdoor Injection on LLMs
SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression
Monitoring Decomposition Attacks in LLMs with Lightweight Sequential Monitors
DAVSP: Safety Alignment for Large Vision-Language Models via Deep Aligned Visual Safety Prompt
From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring
AdversariaL attacK sAfety aLIgnment(ALKALI): Safeguarding LLMs through GRACE: Geometric Representation-Aware Contrastive Enhancement- Introducing Adversarial Vulnerability Quality Index (AVQI)
Refusal-Feature-guided Teacher for Safe Finetuning via Data Filtering and Alignment Distillation
Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models
RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards
From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment
Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets
Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning
BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage
DiaBlo: Diagonal Blocks Are Sufficient For Finetuning
Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models
Bootstrapping LLM Robustness for VLM Safety via Reducing the Pretraining Modality Gap
TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data Synthesis
AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models
EVOREFUSE: Evolutionary Prompt Optimization for Evaluation and Mitigation of LLM Over-Refusal to Pseudo-Malicious Instructions
SafeCOMM: What about Safety Alignment in Fine-Tuned Telecom Large Language Models?
Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack
PoisonSwarm: Universal Harmful Information Synthesis via Model Crowdsourcing
OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models
SOSBENCH: Benchmarking Safety Alignment on Scientific Knowledge
Reshaping Representation Space to Balance the Safety and Over-rejection in Large Audio Language Models
Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.