benign-instruction-bench
lzwhehe/benign-instruction-benchRe-evaluating prompt-injection detectors on LLM agent tool outputs (paper draft, scripts, scores)
ai-securitydefensive-toolseducation+3
lzwhehe/benign-instruction-benchRe-evaluating prompt-injection detectors on LLM agent tool outputs (paper draft, scripts, scores)
hoodoer/colonelclusteredA Java Burp Plugin that performs text clustering on responses to identify outliers/groups based on the actual content of the server responses, say…
rbidou/pyraspRuntime Application Self Protection for Python web servers, serverless functions and MCP servers, detecting attacks, prompt injection and data leaks…
euph00/zoneclaw-codeBenchmark and defense code for persistent memory attacks on OpenClaw-style computer-use agents, with memory-zoning mitigation, attack scenarios, and…
sliu11-byte/mea-benchA lifecycle benchmark for black-box LLM extraction attacks, defenses, and adaptive attacks.
js-lee-ai/refusal-relocatesRefusal localizes, the damage relocates, safety layers under few-sample fine-tuning
liuz233/hardeResearch code for HARDE, an agent harness that probes and adaptively optimizes components for runtime risk detection and execution control across…
kevinchunye/prompt_injectionBenchmark harness measuring where prompt injection defenses fire in tool-using LLM agent pipelines, tracking canary tokens across exposed, persisted,…
joshuaprovoste/deserializerAST-based Static Code Analyzer with Agentic LLM-Powered Relationship Mapping to discover Python RCE paths and deep deserialization chains on AI, LLM,…
guzonghua/awesome-latency-attacksCurated index of deep learning latency, energy-latency & timing (availability) attacks and defenses — companion to the ACM Computing Surveys…
facebookresearch/meta_secalignOpen-weight LLMs and training/evaluation code for defending against prompt injection attacks, with benchmarks for agentic tool-calling and…
kaill-jlq/mmskillriskBenchmark and evaluation harness testing whether LLM agents resist malicious instructions hidden in multimodal skill images, with 108 cases across…
zju-llm-safety/traceAgentic jailbreak framework for LLM-based agents using scheme-based task decomposition, multi-turn disguising strategies, and adaptive self-evolution…
zju-llm-safety/darwinEvolutionary LLM jailbreak and guardrail framework that grows a reusable strategy pool via genetic mutation, Markov selection, and online adversarial…
albert-y1n/piforgeOpen framework for RL-based prompt injection red teaming, with a shared trainer, curriculum learning, and benchmarks like AgentDojo, InjecAgent, and…
123wwwa/flownameNext-generation JavaScript identifier recovery with LLMs.
wsu-cyber-security-lab-ai/clipguardAdversarial image perturbation tool that uses SAM segmentation and CLIP models to evade AI-based scam image classifiers for security research.
sisl-uri/t-backdoorResearch code implementing T-Backdoor, temporal-trigger backdoor attacks on spiking neural networks using rate, latency, and jitter triggers without…