Tools

suels-group/beyond_asr

Research code for measuring jailbreak attack success rates (ASR and stepwise ASR) against LLMs, with implementations of attacks such as GCG and…

pedrobarcha/memory-injection

Research on persistent prompt injections via memory features in Claude, Gemini, and ChatGPT, with reproduction steps, datasets, and proofs for…

pixee/compaction-laundering

Security research on context compaction in coding agents: shows how forged role labels in untrusted content survive summarization and get executed,…

moontea0416/webmirage

Adversarial image attacks on vision-language web agents, from visual grounding to browser execution

stardust457/sldr

Defense framework that mitigates malicious fine-tuning of LLMs using selective layer recovery and dynamic routing, with training, harmfulness…

treeai-lab/awesome-rag-security

Curated collection of research papers on retrieval-augmented generation security, organized by the SLOT taxonomy covering knowledge poisoning,…

greshake/llm-security

Proof-of-concept demos and research on indirect prompt injection attacks against application-integrated LLMs, covering data exfiltration, remote…

euph00/zoneclaw-code

Benchmark and defense code for persistent memory attacks on OpenClaw-style computer-use agents, with memory-zoning mitigation, attack scenarios, and…

sisl-uri/t-backdoor

Research code implementing T-Backdoor, temporal-trigger backdoor attacks on spiking neural networks using rate, latency, and jitter triggers without…

alex66366/odpure

Black-box input-stage purification defense that neutralizes backdoor attacks on object detectors via corruption, diffusion reconstruction, and DBSCAN…

usama1002/deleting-the-trace

Experiments for control-token chain-of-thought suppression and parser-leniency attacks on tool-using LLM agents

ml-security-research-lab/cachetrap

Research code for a gray-box trojan attack that flips a single KV-cache bit in fine-tuned LLM classifiers and measures per-class attack success rate.

xiaoyan-lisa/defenses-for-tool-integrated-llm

Research code and experiments for defending tool-integrated LLM agents against adversarial attacks, extending Agent Security Bench with new defense…

zhou-cybersecurity-ai/synghost

Syntactic Ghost: An Imperceptible General-purpose Backdoor Attacks on Pre-trained Language Models

phkhanhtrinh23/agas

LLM-driven agentic group shilling attack framework that manipulates black-box collaborative-filtering recommender rankings using adaptive multi-role…

atsukisato/pgm-attack

Research code for poisoning attacks on the PGM-index, demonstrating how to craft adversarial data to degrade learned index performance.

ai45lab/skill-safety-bench

Benchmark for evaluating AI agent safety against attacks embedded in skill-facing context, with 155 cases across 6 risk domains, measuring task…