#1Adversarial ML attack frameworks, evasion techniques, and model robustness evaluation tools.
Kitploit recommended
albert-y1n/pismithPISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses
s3cur3th1ssh1t/nim_dinvokeD/Invoke implementation in Nim
albert-y1n/piforgeOpen framework for RL-based prompt injection red teaming, with a shared trainer, curriculum learning, and benchmarks like AgentDojo, InjecAgent, and…
warpedatom/noisehoundDetection-aware BloodHound attack-path scoring - the quietest route to your objective, calibrated across five detection tiers…
zju-llm-safety/traceAgentic jailbreak framework for LLM-based agents using scheme-based task decomposition, multi-turn disguising strategies, and adaptive self-evolution…
maldev-academy/drmbinviaordinalimportsCreate Anti-Copy DRM Malware
dosx-dev/dotnet_xorcryptorA new simple and powerfull packer for malware
shaheeryasirofficial/smugglemypayloadGenerates HTML smuggling pages that embed and reconstruct files client-side via JavaScript, with payload encoding, chunking, obfuscation, and…
darkcodersc/sharpftpc2A Streamlined FTP-Driven Command and Control Conduit for Interconnecting Remote Systems.
soufianetahiri/teamsntlmleakLeak NTLM via Website tab in teams via MS Office
r3drun3/magnetPurple-team telemetry & simulation toolkit.
s3cur3th1ssh1t/nimshellcodefluctuationShellcodeFluctuation PoC ported to Nim
frank2/blennyA payload delivery system which embeds payloads in an executable's icon file!
es0j/execaslr-ekopartyProof-of-concept exploit that bypasses ASLR on Intel CPUs by abusing branch target buffer and speculative execution to leak randomized addresses via…
matheusht/redthreadAn autonomous red-teaming engine for LLMs. RedThread manages the full security lifecycle: generating adversarial attacks, executing precision…
imabee101/cve-2023-44487PoC script for HTTP/2 Rapid Reset (CVE-2023-44487) that sends crafted HTTP/2 streams to trigger denial-of-service conditions on vulnerable servers,…
josh-blythe/bordair-multimodalOpen-source cross-modal and multimodal prompt injection test suite. 250,000+ attack payloads across text, image, document, and audio modalities.…
