Tools

sliu11-byte/mea-bench

A lifecycle benchmark for black-box LLM extraction attacks, defenses, and adaptive attacks.

js-lee-ai/refusal-relocates

Refusal localizes, the damage relocates, safety layers under few-sample fine-tuning

kevinchunye/prompt_injection

Benchmark harness measuring where prompt injection defenses fire in tool-using LLM agent pipelines, tracking canary tokens across exposed, persisted,…

guzonghua/awesome-latency-attacks

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

facebookresearch/meta_secalign

Open-weight LLMs and training/evaluation code for defending against prompt injection attacks, with benchmarks for agentic tool-calling and…

kaill-jlq/mmskillrisk

Benchmark and evaluation harness testing whether LLM agents resist malicious instructions hidden in multimodal skill images, with 108 cases across…

zju-llm-safety/trace

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

zju-llm-safety/darwin

Evolutionary LLM jailbreak and guardrail framework that grows a reusable strategy pool via genetic mutation, Markov selection, and online adversarial…

albert-y1n/piforge

Open framework for RL-based prompt injection red teaming, with a shared trainer, curriculum learning, and benchmarks like AgentDojo, InjecAgent, and…

wsu-cyber-security-lab-ai/clipguard

Adversarial image perturbation tool that uses SAM segmentation and CLIP models to evade AI-based scam image classifiers for security research.

sisl-uri/t-backdoor

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

azzzzliao/aegis-audio-defense

Defense framework that keeps audio-language models frozen and adds a mid-layer risk gate with late-layer safety adapters to block audio jailbreaks at…

alex66366/odpure

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

norrrrrrr-lyn/wainjectbench

Benchmarking prompt injection detections for web agents.

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…