PurCL / ProSecLinks
Official repo for "ProSec: Fortifying Code LLMs with Proactive Security Alignment"
☆14Updated 2 months ago
Alternatives and similar repositories for ProSec
Users that are interested in ProSec are comparing it to the libraries listed below
Sorting:
- ☆20Updated last year
- ☆42Updated 10 months ago
- Code for the AAAI 2023 paper "CodeAttack: Code-based Adversarial Attacks for Pre-Trained Programming Language Models☆30Updated 2 years ago
- [NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents☆35Updated last month
- Simultaneous evaluation on both functionality and security of LLM-generated code.☆17Updated 4 months ago
- Backdooring Neural Code Search☆13Updated last year
- Machine Learning & Security Seminar @Purdue University☆25Updated 2 years ago
- Official repo for FSE'24 paper "CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking"☆16Updated 2 months ago
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆54Updated 3 months ago
- ☆25Updated 8 months ago
- ☆28Updated 7 months ago
- A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.☆60Updated 2 weeks ago
- ☆114Updated 10 months ago
- ☆16Updated 9 months ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆64Updated 7 months ago
- official implementation of [USENIX Sec'25] StruQ: Defending Against Prompt Injection with Structured Queries☆36Updated 2 weeks ago
- Code for paper "SrcMarker: Dual-Channel Source Code Watermarking via Scalable Code Transformations" (IEEE S&P 2024)☆26Updated 9 months ago
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆42Updated 7 months ago
- This is the official code repository for paper "Exploiting the Adversarial Example Vulnerability of Transfer Learning of Source Code".☆11Updated 2 weeks ago
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆126Updated last month
- A toolkit to assess data privacy in LLMs (under development)☆57Updated 5 months ago
- [CIKM 2024] Trojan Activation Attack: Attack Large Language Models using Activation Steering for Safety-Alignment.☆23Updated 10 months ago
- Official Code for ACL 2024 paper "GradSafe: Detecting Unsafe Prompts for LLMs via Safety-Critical Gradient Analysis"☆56Updated 7 months ago
- Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022☆29Updated 2 years ago
- All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks☆16Updated last year
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆48Updated 2 months ago
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆36Updated 10 months ago
- [NeurIPS 2024] Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling☆28Updated 6 months ago
- XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts☆31Updated 11 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆93Updated last year