qingjiesjtu / USCLinks
This is the code repository of our submission: Understanding the Dark Side of LLMs’ Intrinsic Self-Correction.
☆63Updated 9 months ago
Alternatives and similar repositories for USC
Users that are interested in USC are comparing it to the libraries listed below
Sorting:
- A curated list of trustworthy Generative AI papers. Daily updating...☆74Updated last year
- ☆35Updated 11 months ago
- ☆14Updated this week
- ☆30Updated last year
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆58Updated 2 years ago
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆39Updated last year
- Comprehensive Assessment of Trustworthiness in Multimodal Foundation Models☆22Updated 6 months ago
- ☆25Updated 2 years ago
- Distribution Preserving Backdoor Attack in Self-supervised Learning☆17Updated last year
- Repository for Towards Codable Watermarking for Large Language Models☆38Updated 2 years ago
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆52Updated 10 months ago
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆39Updated last year
- Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks (IEEE S&P 2024)☆34Updated 2 months ago
- Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"☆18Updated 4 months ago
- ☆83Updated 4 years ago
- ☆20Updated 6 months ago
- ☆27Updated 2 years ago
- A toolbox for backdoor attacks.☆22Updated 2 years ago
- ☆31Updated 3 years ago
- [NeurIPS 2024] Fight Back Against Jailbreaking via Prompt Adversarial Tuning☆10Updated 10 months ago
- ☆50Updated last year
- This is the code repository for "Uncovering Safety Risks of Large Language Models through Concept Activation Vector"☆44Updated 10 months ago
- ☆20Updated last year
- ☆101Updated last year
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆54Updated 8 months ago
- ☆62Updated 3 months ago
- [CCS-LAMPS'24] LLM IP Protection Against Model Merging☆15Updated 11 months ago
- The official implementation of USENIX Security'23 paper "Meta-Sift" -- Ten minutes or less to find a 1000-size or larger clean subset on …☆19Updated 2 years ago
- [NDSS'25] The official implementation of safety misalignment.☆16Updated 8 months ago
- Simulator.☆103Updated 5 months ago