Tools

phil-fan/fs-attack

Implementation of the paper "Rethinking Latency Denial-of-Service: Attack the LLM Serving Framework, Not the Model"

deep-jlu/skillpoison

Research pipeline that constructs verified successful experiences and organizes them into formation records to progressively poison model skills via…

guzonghua/awesome-latency-attacks

Curated index of deep learning latency, energy-latency & timing (availability) attacks and defenses — companion to the ACM Computing Surveys…

zju-llm-safety/trace

Agentic jailbreak framework for LLM-based agents using scheme-based task decomposition, multi-turn disguising strategies, and adaptive self-evolution…

shaheeryasirofficial/smugglemypayload

Generates HTML smuggling pages that embed and reconstruct files client-side via JavaScript, with payload encoding, chunking, obfuscation, and…

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.

atsukisato/pgm-attack

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

davidcarliez/trustmebro

Bypass llm guardrails by confusing it with fabricated tool output.

george0papasotiriou/llm-jailbreak-via-chain-of-logic-injection-cve-2026-3098

Multi-stage prompt injection technique that bypasses LLM safety alignment via identity reassignment, refusal suppression, and output coercion,…

ricardojoserf/crystalpotato

Crystal port of GodPotato to abuse SeImpersonatePrivilege with indirect syscalls, dynamic API resolution and compile-time string obfuscation. Run…

cleverhans-lab/cleverhans

An adversarial example library for constructing attacks, building defenses, and benchmarking both

ccob/threadlessinject

Threadless Process Injection using remote function hooking.

mgeeky/shellcodefluctuation

An advanced in-memory evasion technique fluctuating shellcode's memory protection between RW/NoAccess & RX and then encrypting/decrypting its contents

misp/misp-galaxy

Clusters and elements to attach to MISP events or attributes (like threat actors)

promptfoo/modelaudit

Security scanner for AI/ML model files. Detects malicious code, backdoors, and vulnerabilities before deployment

mthamil107/db_audit_research

Self-Defeating Audits: reproducible lab showing a low-privilege PostgreSQL role reversibly blinding a trigger-based auditor + poisoning attribution…