#1Adversarial ML attack frameworks, evasion techniques, and model robustness evaluation tools.
Kitploit recommended
breachsimrange/redteamsimmerWeb-based adversary emulation platform that orchestrates Atomic Red Team tests across Windows endpoints via Go agents, with MITRE ATT&CK mapping, APT…
pixee/compaction-launderingSecurity research on context compaction in coding agents: shows how forged role labels in untrusted content survive summarization and get executed,…
cybrly/badsuccessorExploits the Windows Server 2025 dMSA privilege escalation vulnerability to enumerate writable OUs, escalate to arbitrary domain users, extract…
guillaumemeyer/watermarks-removerA privacy-first app that strips AI watermarks from content you own.
meridianlabs-ai/inspect_petriAn alignment auditing agent capable of quickly exploring alignment hypothesis
lsudoko/antibodyGitLab Duo DevSecOps loop where a second AI re-attacks every AI-written fix, saving each successful bypass as a permanent antibody replayed in CI and…
mastyf-ai/mastyf.aiOpen-source AI security platform providing perimeter defense for LLMs and AI agents through swarm analysis, policy enforcement, adversarial testing,…
promptfoo/modelauditSecurity scanner for AI/ML model files. Detects malicious code, backdoors, and vulnerabilities before deployment
suels-group/beyond_asrResearch code for measuring jailbreak attack success rates (ASR and stepwise ASR) against LLMs, with implementations of attacks such as GCG and…
dovughs/mora-hwbpHardware Breakpoint (DR0-DR7) based patch-less user-mode hooking & telemetry instrumentation engine (AMSI, WLDP & ETW PoC).
ericyoc/ai-security-literacyReproducible Colab pipeline that grounds six AI Security Literacy competency dimensions in public benchmarks and survey microdata, producing figures,…
ukanwat/guardrebindResearch code, benchmark and defense for target rebinding attacks that trick LLM safety guards into grading forged decoy content, plus segment-max…
goochbeater/spiritual-spell-red-teamingA repo for jailbreaking various LLMs, mainly Claude
aniketkarne/aco-prompt-shieldStop prompt injection attacks before they reach your LLM — zero API costs, runs entirely locally, integrates in 2 minutes. Prompt injection is the…
shaheeryasirofficial/smugglemypayloadGenerates HTML smuggling pages that embed and reconstruct files client-side via JavaScript, with payload encoding, chunking, obfuscation, and…
meta-llama/purplellamaSet of tools to assess and improve LLM security.
yzhao062/pyodA Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 60+ detectors, benchmark-backed ADEngine…
phkhanhtrinh23/agasLLM-driven agentic group shilling attack framework that manipulates black-box collaborative-filtering recommender rankings using adaptive multi-role…
