zichuan-liu / IB4LLMsLinks
[NeurIPS'24] Protecting Your LLMs with Information Bottleneck
☆22Updated last year
Alternatives and similar repositories for IB4LLMs
Users that are interested in IB4LLMs are comparing it to the libraries listed below
Sorting:
- A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.☆71Updated 6 months ago
- The repository of the paper "REEF: Representation Encoding Fingerprints for Large Language Models," aims to protect the IP of open-source…☆68Updated 10 months ago
- [ICLR 2025] Dissecting adversarial robustness of multimodal language model agents☆115Updated 9 months ago
- ☆50Updated 9 months ago
- Official implementation for "ALI-Agent: Assessing LLMs'Alignment with Human Values via Agent-based Evaluation"☆21Updated 3 months ago
- [ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast☆117Updated last year
- Code repo for the paper: Attacking Vision-Language Computer Agents via Pop-ups☆47Updated 11 months ago
- ☆18Updated last month
- Code and data for paper "A Semantic Invariant Robust Watermark for Large Language Models" accepted by ICLR 2024.☆35Updated last year
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆32Updated last year
- Our research proposes a novel MoGU framework that improves LLMs' safety while preserving their usability.☆18Updated 10 months ago
- ☆75Updated 3 months ago
- ☆153Updated last year
- ☆35Updated last year
- ☆30Updated last year
- ☆22Updated last year
- ☆18Updated 7 months ago
- Codes for our paper "AgentMonitor: A Plug-and-Play Framework for Predictive and Secure Multi-Agent Systems"☆13Updated 11 months ago
- An official implementation of "Catastrophic Failure of LLM Unlearning via Quantization" (ICLR 2025)☆35Updated 9 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆98Updated last year
- This repo is for the safety topic, including attacks, defenses and studies related to reasoning and RL☆52Updated 2 months ago
- [ACL 2025] Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms☆29Updated 5 months ago
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)☆62Updated last year
- ☆25Updated 8 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆65Updated 10 months ago
- Can Knowledge Editing Really Correct Hallucinations? (ICLR 2025)☆27Updated 3 months ago
- Improving Your Model Ranking on Chatbot Arena by Vote Rigging (ICML 2025)☆24Updated 9 months ago
- ☆188Updated 2 years ago
- ☆42Updated 2 weeks ago
- ☆23Updated 10 months ago