Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack
cs.AI
Submitted: 2026-06-04
Updated: 2026-09-27
Code: https://github.com/iNLP-Lab/Safety-Paradox
Terminology
Sources
- GPT-4 Technical Report
- gpt-oss-120b & gpt-oss-20b Model Card
- Training Verifiers to Solve Math Word Problems
- The Llama 3 Herd of Models
- Deliberative Alignment: Reasoning Enables Safer Language Models
- WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
- Measuring Massive Multitask Language Understanding
- GPT-4o System Card
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- Mistral 7B
- DeepInception: Hypnotize Large Language Model to Be Jailbreaker
- DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
- CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models
- Qwen2.5 Technical Report
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- OpenAI GPT-5 System Card
- Gemma 2: Improving Open Language Models at a Practical Size
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Ethical and social risks of harm from Language Models
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection