OMLASP
telefonica/omlaspFramework for auditing machine learning algorithms against adversarial attacks and biases, providing educational tools and an academic paper to…
adversarial-attackai-securityeducation+2
22
telefonica/omlaspFramework for auditing machine learning algorithms against adversarial attacks and biases, providing educational tools and an academic paper to…
p-e-w/hereticFully automatic censorship removal for language models
apache/spamassassinOpen-source email filtering framework that detects spam and phishing using content analysis, header checks, Bayesian scoring, and DNS blocklists.
nameles-org/namelesOpen source entropy based invalid traffic detection and pre-bid filtering.
trailofbits/ficklingA Python pickling decompiler and static analyzer
mandiant/stringsifterA machine learning tool that ranks strings based on their relevance for malware analysis.
jianshuod/ipi-exposure-signalResearch pipeline for detecting latent indirect prompt-injection exposure signals in agentic LLMs via hidden-state probing, including trace…
online-ml/riverStreaming machine learning library for incremental learning on data streams, providing online estimators, drift and anomaly detection, pipelines,…
otrf/security-datasetsRe-play Security Events
thunlp/openattackAn Open-Source Package for Textual Adversarial Attack.
tracebyte8/systraceLinux system-call monitor using ptrace to trace file, process, network, and memory activity, with namespace isolation and machine learning…
pppyb/secopdResearch implementation for mitigating adaptive prompt injections via on-policy distillation, with training recipes and evaluators for SEP, PISmith,…
spiralbl0ck/ai_hackingCollection of CVE(work) on tenserflow binary pwning it
kreotic/sentrygridML-driven threat detection and continuous monitoring platform built for federal zero trust architectures.
philarkwright/dga-detectionDGA Domain Detection using Bigram Frequency Analysis
thuyimingli/backdoor-learning-resourcesCurated list of backdoor learning papers, surveys, and toolboxes, organizing poisoning-based attacks and defenses in deep learning for researchers…
nvidia-nemo/guardrailsProgrammable guardrails for LLM chat apps: enforce input/output rails, block jailbreaks and prompt injections, detect hallucination, and mask…
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…