CacheTrap
ml-security-research-lab/cachetrapResearch code for a gray-box trojan attack that flips a single KV-cache bit in fine-tuned LLM classifiers and measures per-class attack success rate.
adversarial-attackai-securitymachine-learning+2
1
ml-security-research-lab/cachetrapResearch code for a gray-box trojan attack that flips a single KV-cache bit in fine-tuned LLM classifiers and measures per-class attack success rate.
shuangliangx/learning-to-detectDetects unknown jailbreak attacks in large vision-language models using hidden state analysis and autoencoders, with training and evaluation…
vinsontang1/dcvdThe code in "DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization"
binzhwang/tnc-defenseResearch code for detecting and detoxifying backdoors in text-to-image diffusion models, with pipelines for Stable Diffusion v1.4, v1.5, XL, and 3…
c2a2-at-florida-atlantic-university/gr-physecGNU Radio module for physical layer security using deep learning channel fingerprinting, feature quantization, and SHA3-512 key generation from SDR…
xrazymee/ragsieveSelf-referenced local contrast for knowledge-poison detection in retrieval-augmented generation
kreotic/sentrygridML-driven threat detection and continuous monitoring platform built for federal zero trust architectures.
atsukisato/pgm-attackResearch code for poisoning attacks on the PGM-index, demonstrating how to craft adversarial data to degrade learned index performance.
alphawarheads/watermark_spoofingResearch code and dataset (WSD) for evaluating audio watermarking impact on anti-spoofing, using wav2vec2 XLS-R and knowledge-preserving learning.
renweimeng/vlun-agent-xVulnAgent-X: A Layered Agentic Framework for Repository-Level Vulnerability Detection
trustedsec/ts_llmlibPython library for local LLM-powered security analysis with Ghidra binary analysis, C/C++ vulnerability scanning, and MCP tool integration for…
yumlembam/insider-threatGraph-based insider threat detection using GCN-BiLSTM and attention models on CMU CERT datasets. Includes data preprocessing, feature extraction, and…
quevatech/challenge_repoStructured challenge repository offering bounties for breaking a neural-network-based random number generator validated against NIST SP 800-22 and SP…
sastraadiwiguna-purpleeliteteaming/ddos-purple-teaming-offensive-multi-vector-7-tier-defensive-holistic-blueprint-Replicable Blueprint for advanced DDoS Purple Teaming, engineered for the threat landscape. It integrates a Red Elite Teaming offensive…
mannansainicyber/url_checkerHybrid ML and heuristic-based URL phishing detector with real-time analysis, explainable confidence scores, and REST API for programmatic security…
cyhe50/cve-2025-32434-pocProof-of-concept exploit for CVE-2025-32434, a pickle deserialization vulnerability in PyTorch's weights_only mode, demonstrating malicious tar file…
xiaoyan-lisa/defenses-for-tool-integrated-llmResearch code and experiments for defending tool-integrated LLM agents against adversarial attacks, extending Agent Security Bench with new defense…
mcastens/alycon-threat-landscapeTraining-free anomaly detection framework using Shannon Entropy, Fisher Information, and Wasserstein Distance to map system states into geometrically…