hanxi19/black_hole_attack_for_vector_databaseResearch implementation of the Black-Hole Attack that poisons vector database indexes via centrality-driven hubness, with FAISS pipelines and…
cosmosyi/autocontrol-arenaAutomated framework for frontier AI safety evaluation that synthesizes executable, pressure-rich test environments to uncover latent risks in…
yxf203/defense-as-skillRuntime guard skill that detects and blocks malicious skill-induced attacks in skill-augmented agents, with an MCTS loop that evolves the guard…
krxi/asmsenseSmall language model that names and describes functions in stripped x86-64 binaries, with an open dataset, baselines, and LoRA fine-tuning…
stardust457/sldrDefense framework that mitigates malicious fine-tuning of LLMs using selective layer recovery and dynamic routing, with training, harmfulness…
danigil/neupermZero-retraining sanitization that reorders permutation-equivalent neural network units to destroy malware embedded via weight-steganography attacks…
graph-com/cka-agentResearch implementation of an LLM jailbreak agent that bypasses commercial model guardrails using harmless prompt weaving and adaptive tree search.
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…
deep-jlu/skillpoisonResearch pipeline that constructs verified successful experiences and organizes them into formation records to progressively poison model skills via…
zju-llm-safety/ascentFine-tuning framework that applies first-order optimal safety calibration and periodic recalibration to LLMs, preserving safety-compatible updates…
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…
liuz233/hardeResearch code for HARDE, an agent harness that probes and adaptively optimizes components for runtime risk detection and execution control across…
zju-llm-safety/darwinEvolutionary LLM jailbreak and guardrail framework that grows a reusable strategy pool via genetic mutation, Markov selection, and online adversarial…
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.
azzzzliao/aegis-audio-defenseDefense framework that keeps audio-language models frozen and adds a mid-layer risk gate with late-layer safety adapters to block audio jailbreaks at…
atomdrift-project/scan0-day malware detection for binaries, source & scripts (that doesn't suck)
cbuijs/sdproxyDNS Proxy that is simple and fast with not so simple features. Focused on routed DNS forwarding, filtering and parental control.
alex66366/odpureBlack-box input-stage purification defense that neutralizes backdoor attacks on object detectors via corruption, diffusion reconstruction, and DBSCAN…
