mlily2024/final-project-sql-injection-pipelineHybrid machine-learning pipelines for detecting SQL injection in web traffic, combining DistilBERT and BERT-GNN models with adversarial training and…
threatrecall/zettelforgeAgentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain…
iqsec-lab/freemocaMemory-free continual learning framework for malware classification using mode connectivity-based interpolation. Supports class-incremental and…
salesforce/merlionEnd-to-end Python framework for time series intelligence, offering anomaly detection, forecasting, change point detection, AutoML, ensembles, and…
tancik/stegastampInvisible Hyperlinks in Physical Photographs
yeasen-z/leakgaugeDetects LLM context-leakage attacks by training lightweight behavior probes on log-probabilities, with vLLM offline/server detection pipelines.
alphawarheads/watermark_spoofingResearch code and dataset (WSD) for evaluating audio watermarking impact on anti-spoofing, using wav2vec2 XLS-R and knowledge-preserving learning.
q-rz/saffronInference scaling for LLM safety assurance
afbf4c8996f/jammer-locImplements machine and deep learning methods for indoor UWB jammer localization, including hyperparameter optimization, classification, and…
trailofbits/anamorpherimage scaling attacks for multi-modal prompt injection
sevuldet/sevuldetA Semantics-Enhanced Learnable Vulnerability Detector
promptfoo/modelauditSecurity scanner for AI/ML model files. Detects malicious code, backdoors, and vulnerabilities before deployment
vinsontang1/vultriageThe code of VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detection
vinsontang1/dcvdThe code in "DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization"
pr0me/xtrideN-gram-based type recovery tool for binaries, recovering structures and function signatures from decompiled code with high throughput and actionable…
cookiengineer/exocompSelf-hosted multi-agent environment for Go with LLM-powered pentesting agents (exploiter, reverser, threathunter, webscanner) that automate…
bytepro-ai/bitcoder-v2-researchResearch repository documenting LLM generalization ceilings in code security vulnerability detection, with cross-evaluation across synthetic and…
nvidia-nemo/guardrailsProgrammable guardrails for LLM chat apps: enforce input/output rails, block jailbreaks and prompt injections, detect hallucination, and mask…
