#1Adversarial ML attack frameworks, evasion techniques, and model robustness evaluation tools.
Kitploit recommended
phkhanhtrinh23/agasLLM-driven agentic group shilling attack framework that manipulates black-box collaborative-filtering recommender rankings using adaptive multi-role…
uiuc-kang-lab/persistbdResearch code for training adapters that make LLM agent backdoors survive benign fine-tuning, with trigger-rate scoring, SWE-bench evaluation, and…
lassnajmuldeen/balcony-jailbreakingJailbreak vulnerability across early-exit depths LLMs. Published at NeurIPS 2026 in the FLMSec workshop
ye-ze-yu/epireal-benchRed-teaming benchmark and black-box attack framework for evaluating visual misinformation risks in commercial image generators, with 10k false-claim…
moontea0416/webmirageAdversarial image attacks on vision-language web agents, from visual grounding to browser execution
deep-jlu/skillpoisonResearch pipeline that constructs verified successful experiences and organizes them into formation records to progressively poison model skills via…
js-lee-ai/refusal-relocatesLLM safety: analyze how fine-tuning shifts refusal behavior and evaluate layer-freezing and low-rank defenses.
zju-llm-safety/ascentFine-tuning framework that applies first-order optimal safety calibration and periodic recalibration to LLMs, preserving safety-compatible updates…
jiep/offensive-ai-compilationA curated list of useful resources that cover Offensive AI.
phil-fan/fs-attackImplementation of the paper "Rethinking Latency Denial-of-Service: Attack the LLM Serving Framework, Not the Model"
stardust457/sldrDefense framework that mitigates malicious fine-tuning of LLMs using selective layer recovery and dynamic routing, with training, harmfulness…
zju-llm-safety/traceAgentic jailbreak framework for LLM-based agents using scheme-based task decomposition, multi-turn disguising strategies, and adaptive self-evolution…
sliu11-byte/mea-benchA lifecycle benchmark for black-box LLM extraction attacks, defenses, and adaptive attacks.
kevinchunye/prompt_injectionBenchmark harness measuring where prompt injection defenses fire in tool-using LLM agent pipelines, tracking canary tokens across exposed, persisted,…
facebookincubator/ttpforgeThe TTPForge is a Cybersecurity Framework for developing, automating, and executing attacker Tactics, Techniques, and Procedures (TTPs).
multimodal-ai-lab/tobacToken by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models (NeurIPS'26)
kaill-jlq/mmskillriskBenchmark and evaluation harness testing whether LLM agents resist malicious instructions hidden in multimodal skill images, with 108 cases across…
albert-y1n/piforgeOpen framework for RL-based prompt injection red teaming, with a shared trainer, curriculum learning, and benchmarks like AgentDojo, InjecAgent, and…
