Tools

pixee/compaction-laundering

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

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…

phkhanhtrinh23/agas

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

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…

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.

sisl-uri/t-backdoor

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

usama1002/deleting-the-trace

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

alex66366/odpure

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

rosesecurity/anti-virus-evading-payloads

During the exploitation phase of a pen test or ethical hacking engagement, you will ultimately need to try to cause code to run on target system…

treeai-lab/awesome-rag-security

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

jinxhy/awesome-moai-security

Curated reading list and taxonomy of attack and defense research for mobile on-device AI systems, covering adversarial, backdoor, model stealing, and…

atsukisato/pgm-attack

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

yeasen-z/leakgauge

Detects LLM context-leakage attacks by training lightweight behavior probes on log-probabilities, with vLLM offline/server detection pipelines.

camillegr/cve-2026-73292

Proof-of-concept exploit for CVE-2026-73292: CSRF attack on Semaphore UI password change endpoint, serving a malicious page that silently resets an…

cenobyte-vincit/xspawn

Spawns macOS programs through launchd's private XPC interface without execing them, making EDR record launchd as parent. Supports one-shot,…

ezramansor/cve-2025-32432-poc

A simple PoC on the Remote Code Execution (RCE) Vulnerability of CraftCMS designated as CVE-2025-32432 written in Go