neelsjain / baseline-defensesLinks
Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"
☆25Updated last year
Alternatives and similar repositories for baseline-defenses
Users that are interested in baseline-defenses are comparing it to the libraries listed below
Sorting:
- Comprehensive Assessment of Trustworthiness in Multimodal Foundation Models☆21Updated 3 months ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆53Updated 10 months ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆51Updated 8 months ago
- An unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)☆42Updated last year
- Code and data to go with the Zhu et al. paper "An Objective for Nuanced LLM Jailbreaks"☆32Updated 6 months ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆50Updated 5 months ago
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆144Updated 4 months ago
- ☆47Updated 2 months ago
- [NeurIPS 2024] Fight Back Against Jailbreaking via Prompt Adversarial Tuning☆10Updated 7 months ago
- ☆20Updated last year
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆46Updated 8 months ago
- ☆20Updated 6 months ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆20Updated 11 months ago
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆24Updated 11 months ago
- To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models☆31Updated last month
- Accepted by ECCV 2024☆139Updated 8 months ago
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆55Updated 3 months ago
- This is the code repository for "Uncovering Safety Risks of Large Language Models through Concept Activation Vector"☆39Updated 7 months ago
- ☆16Updated 3 months ago
- ☆22Updated 3 months ago
- Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"☆14Updated last month
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆61Updated 5 months ago
- All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks☆17Updated last year
- ☆28Updated 8 months ago
- ☆29Updated last month
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆55Updated last year
- Code for ICLR 2025 Failures to Find Transferable Image Jailbreaks Between Vision-Language Models☆29Updated 3 weeks ago
- [NeurIPS 2024] Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling☆29Updated 7 months ago
- [CIKM 2024] Trojan Activation Attack: Attack Large Language Models using Activation Steering for Safety-Alignment.☆24Updated 10 months ago
- This is the official code for the paper "Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable".☆18Updated 3 months ago