PurCL / ProSecLinks
Official repo for "ProSec: Fortifying Code LLMs with Proactive Security Alignment"
โ15Updated 6 months ago
Alternatives and similar repositories for ProSec
Users that are interested in ProSec are comparing it to the libraries listed below
Sorting:
- โ49Updated last year
- ๐ฎReasoning for Safer Code Generation; ๐ฅWinner Solution of Amazon Nova AI Challenge 2025โ26Updated last month
- โ20Updated last year
- Code for the AAAI 2023 paper "CodeAttack: Code-based Adversarial Attacks for Pre-Trained Programming Language Modelsโ33Updated 2 years ago
- [NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agentsโ49Updated 2 months ago
- โ122Updated last year
- Machine Learning & Security Seminar @Purdue Universityโ25Updated 2 years ago
- Adversarial Attack for Pre-trained Code Modelsโ10Updated 3 years ago
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"โ69Updated 2 months ago
- Backdooring Neural Code Searchโ14Updated 2 years ago
- Official repo for FSE'24 paper "CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking"โ16Updated 6 months ago
- [NeurIPS'24] SemCoder: Training Code Language Models with Comprehensive Semantics Reasoningโ25Updated 10 months ago
- Repository for "SecurityEval Dataset: Mining Vulnerability Examples to Evaluate Machine Learning-Based Code Generation Techniques" publisโฆโ78Updated last year
- Simultaneous evaluation on both functionality and security of LLM-generated code.โ27Updated 3 weeks ago
- [CCS 2024] Optimization-based Prompt Injection Attack to LLM-as-a-Judgeโ31Updated 3 weeks ago
- ๐ฅ๐ฅ๐ฅ Detecting hidden backdoors in Large Language Models with only black-box accessโ44Updated 4 months ago
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"โ155Updated 5 months ago
- โ46Updated last month
- official implementation of [USENIX Sec'25] StruQ: Defending Against Prompt Injection with Structured Queriesโ45Updated 2 months ago
- Official Implementation of NeurIPS 2024 paper - BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokensโ24Updated 6 months ago
- โ34Updated last year
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873โ165Updated last year
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]โ91Updated last year
- โ35Updated 11 months ago
- Code to generate NeuralExecs (prompt injection for LLMs)โ24Updated 10 months ago
- XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Expertsโ35Updated last year
- Code for paper "SrcMarker: Dual-Channel Source Code Watermarking via Scalable Code Transformations" (IEEE S&P 2024)โ30Updated last year
- The official repository for guided jailbreak benchmarkโ20Updated 2 months ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLMโ71Updated 11 months ago
- Agent Security Bench (ASB)โ124Updated this week