Towards the Worst-case Robustness of Large Language Models
cs.LG
Submitted: 2025-01-31
Updated: 2026-11-06
Terminology
Sources
- Detecting Language Model Attacks with Perplexity
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
- On the Robustness of the CVPR 2018 White-Box Adversarial Example Defenses
- GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs
- Large Language Models as Tool Makers
- On Evaluating Adversarial Robustness
- Are aligned neural networks adversarially aligned?
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
- Your Diffusion Model is Secretly a Certifiably Robust Classifier
- Training Verifiers to Solve Math Word Problems
- Large Language Models for Compiler Optimization
- Multilingual Jailbreak Challenges in Large Language Models
- The Llama 3 Herd of Models
- Improved Large Language Model Jailbreak Detection via Pretrained Embeddings
- Measuring Massive Multitask Language Understanding
- Certified Robustness to Clean-Label Poisoning Using Diffusion Denoising
- Toxicity Detection for Free
- Baseline Defenses for Adversarial Attacks Against Aligned Language Models
- Improved Techniques for Optimization-Based Jailbreaking on Large Language Models
- Certifying LLM Safety against Adversarial Prompting
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning