https://wiki.offsecml.com/Supply+Chain+Attacks/Public+Model+Registries/Using+a+Huggingface+Watering+Holehttps://wiki.offsecml.com/Supply+Chain+Attacks/Models/Using+the+ONNX+Runtimehttps://wiki.offsecml.com/Supply+Chain+Attacks/Models/Using+Keras+Lambda+Layershttps://wiki.offsecml.com/Supply+Chain+Attacks/Datasets/Practical+Poisoning++of+Web-Scale+Training+Datasetshttps://wiki.offsecml.com/Offensive+ML/Flywheels/Nemesishttps://wiki.offsecml.com/Supply+Chain+Attacks/MLops+Pipeline+Tooling/Using+Jupyterhttps://wiki.offsecml.com/Supply+Chain+Attacks/MLops+Pipeline+Tooling/Using+kservehttps://wiki.offsecml.com/Supply+Chain+Attacks/MLops+Pipeline+Tooling/Using+flowisehttps://wiki.offsecml.com/Supply+Chain+Attacks/MLops+Pipeline+Tooling/Using+Rayhttps://wiki.offsecml.com/Supply+Chain+Attacks/MLops+Pipeline+Tooling/Using+Omniboard+-+wiphttps://wiki.offsecml.com/Supply+Chain+Attacks/MLops+Pipeline+Tooling/Using+MLflowhttps://wiki.offsecml.com/Supply+Chain+Attacks/MLops+Pipeline+Tooling/Using+Kubeflowhttps://wiki.offsecml.com/Supply+Chain+Attacks/MLops+Pipeline+Tooling/Using+H20-3https://wiki.offsecml.com/Supply+Chain+Attacks/MLops+Pipeline+Tooling/Using+Airflowhttps://wiki.offsecml.com/Offensive+ML/Scanners/Using+Reinforcement+learning+to+find+privshttps://wiki.offsecml.com/Offensive+ML/Password+Guessers/Using+Deep+Learninghttps://wiki.offsecml.com/Offensive+ML/Obfuscators/Obfuscation+using+markov+chainshttps://wiki.offsecml.com/Offensive+ML/Droppers/Sandbox+detection+using+process+ratioshttps://wiki.offsecml.com/Supply+Chain+Attacks/MLops+Pipeline+Tooling/Recon/discovering+ml+deployment+environmentshttps://wiki.offsecml.com/Offensive+ML/WiFi/Reinforcement+based+DeAuther+and+Handshake+Collectionhttps://wiki.offsecml.com/Welcome+to+the+Offensive+ML+Playbookhttps://wiki.offsecml.com/Offensive+ML/Subdomains/Using+Embeddingshttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+Access+to+Embeddings/Using+Text+Embeddings+Inversionhttps://wiki.offsecml.com/Offensive+ML/Relationship+Graphing/Using+BloodhoundGPT+to+enumerate+ADhttps://wiki.offsecml.com/Adversarial+ML/NLP+Attacks/Using+Model+Access/Using+a+perturbation+frameworkhttps://wiki.offsecml.com/Offensive+ML/Phishing/using+model+inversion+to+reverse+engineer+phishing+detectorshttps://wiki.offsecml.com/Offensive+ML/Phishing/Avoiding+phishing+webpage+detectors+via+black+box+MLhttps://wiki.offsecml.com/Offensive+ML/OSINT/Using+LLMs+to+find+similar+documentshttps://wiki.offsecml.com/Supply+Chain+Attacks/Models/Using+Malicious+Pickleshttps://wiki.offsecml.com/Offensive+ML/Vishing/Voice+Cloning+using+Real+Time+Cloninghttps://wiki.offsecml.com/Supply+Chain+Attacks/GPU+Attacks/Using+access+to+a+GPU+programmable+interfacehttps://wiki.offsecml.com/Adversarial+ML/Image+Attacks/Using+poisoned+concepts+in+visually+similar+imageshttps://wiki.offsecml.com/Supply+Chain+Attacks/Models/Using+Neuron+Based+Steganographyhttps://wiki.offsecml.com/Offensive+ML/CAPTCHA+Solving/Using+a+multi-modal+LLMhttps://wiki.offsecml.com/Supply+Chain+Attacks/MLops+Pipeline+Tooling/Using+ClearMLhttps://wiki.offsecml.com/Offensive+ML/General+Purpose+Hackbots/Using+LLMs+for+general+purpose+offensive+securityhttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+an++API+Endpoint+or+Black+Box/Prompt+Injection/Using+ASCII+Arthttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+an++API+Endpoint+or+Black+Box/Prompt+Injection/Using+a+Tree+of+Attacks+to+automate+jailbreakshttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+an++API+Endpoint+or+Black+Box/Prompt+Injection/Using+a+Multimodal+approachhttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+an++API+Endpoint+or+Black+Box/Prompt+Injection/Using+Repeated+Token+Sequenceshttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+an++API+Endpoint+or+Black+Box/Prompt+Injection/Using+Precise+Character+Sequenceshttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+an++API+Endpoint+or+Black+Box/Prompt+Injection/Using+Emojis+and+Encodingshttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+an++API+Endpoint+or+Black+Box/Prompt+Injection/Using+DAN+or+another+personahttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+an++API+Endpoint+or+Black+Box/Prompt+Injection/Using++Hidden+Encodingshttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+an++API+Endpoint+or+Black+Box/Assess+Harm/Using+PyRIT+to+assess+robustness+against+harmhttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+an++API+Endpoint+or+Black+Box/Prompt+Injection/Visual+Prompt+Injectionhttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+an++API+Endpoint+or+Black+Box/Prompt+Injection/Using+an+adversarial+self-replicating+prompthttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+Access+to+a+Model+Registry/Modify+an+LLMs+ground+truthshttps://wiki.offsecml.com/Offensive+ML/Attacking+Netflow+Classifiers/Poisoning+netflow+classifershttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+an++API+Endpoint+or+Black+Box/To+Steal+Model/Using+the+logit+bias+parameterhttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+an++API+Endpoint+or+Black+Box/Prompt+Injection/Using+a+scanner+to+automate+finding+jailbreakshttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+an++API+Endpoint+or+Black+Box/Prompt+Injection/Using+garak+to+automate+finding+injectionshttps://wiki.offsecml.com/Offensive+ML/Fuzzing/using+adversarial+ML+to+fuzz+web+application+firewallshttps://wiki.offsecml.com/Offensive+ML/Fuzzing/using+LLMS+as+fuzzers+for+codebaseshttps://wiki.offsecml.com/Offensive+ML/OSINT/Using+GenAI+for+location+and+facial+recognitionhttps://wiki.offsecml.com/Offensive+ML/General+Purpose+Hackbots/Benchmarking+hackbots+and+agentshttps://wiki.offsecml.com/Supply+Chain+Attacks/MLops+Pipeline+Tooling/Using+BentoMLhttps://wiki.offsecml.com/Adversarial+ML/Image+Attacks/DNN+Attacks/Visual+System+Attacks/Black+Box/Poisoning/Using+a+Hidden+Trigger+Backdoorhttps://wiki.offsecml.com/Adversarial+ML/Image+Attacks/DNN+Attacks/Visual+System+Attacks/Black+Box/Evasion/Using+Physical+Access/Using+physical+or+digital+light+-+Adversarial+Laser+Beamhttps://wiki.offsecml.com/Adversarial+ML/Image+Attacks/DNN+Attacks/Visual+System+Attacks/Black+Box/Evasion/Using+API+Access+to+a+model/Hop-Skip-Jumphttps://wiki.offsecml.com/Adversarial+ML/Image+Attacks/DNN+Attacks/Inverting+DNN+Models/Using+an+Inversion+Frameworkhttps://wiki.offsecml.com/Offensive+ML/CAPTCHA+Solving/Using+GPT4ohttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+an++API+Endpoint+or+Black+Box/Prompt+Injection/Using+structured+outputshttps://wiki.offsecml.com/Supply+Chain+Attacks/Models/Using+the+model+graph+to+backdoorhttps://wiki.offsecml.com/Supply+Chain+Attacks/Datasets/Practical+Poisoning++of+Pre+Training+Datasetshttps://wiki.offsecml.com/Offensive+ML/Application+Security/Static+Code+analysishttps://wiki.offsecml.com/Offensive+ML/Application+Security/Analyze+API+endpointshttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+an++API+Endpoint+or+Black+Box/Prompt+Injection/Using+obfuscated+adversarial+promptshttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+an++API+Endpoint+or+Black+Box/Prompt+Injection/Using+PALLMS+dataset+to+find+injectionshttps://wiki.offsecml.com/Defensive+ML/Understanding+Models/Using+tmanhttps://wiki.offsecml.com/Defensive+ML/Telemetry/TIG+Stackhttps://wiki.offsecml.com/Defensive+ML/Malware+Classification/Using+Binary+Code+Similarity+Search+to+find+malware+or+vulnerabilitieshttps://wiki.offsecml.com/Defensive+ML/Malware+Classification/Using++ML+to+classify+malwarehttps://wiki.offsecml.com/Defensive+ML/Malware+Classification/Malware+Datasets/Using+a+database+of++malware+sampleshttps://wiki.offsecml.com/Defensive+ML/Malware+Classification/Malware+Datasets/Using+Control+Flow+Graphshttps://wiki.offsecml.com/Defensive+ML/Malware+Classification/Malware+Datasets/Using+a+database+of+malicious+signalshttps://wiki.offsecml.com/Defensive+ML/Malware+Classification/Malware+Datasets/Using+a+database+of++vulnerable+malware+sampleshttps://wiki.offsecml.com/Defensive+ML/Malware+Classification/Labelling+malwarehttps://wiki.offsecml.com/Defensive+ML/Malware+Classification/Extracting+ML+ready+data+from+software+binarieshttps://wiki.offsecml.com/Defensive+ML/Incident+Response/Using+LLMs+to+manage+low-criticality+state+based+alertshttps://wiki.offsecml.com/Defensive+ML/Incident+Response/Using+LLMs+to+generate+Tabletop+scenarioshttps://wiki.offsecml.com/Defensive+ML/Filetype+Classification/Using+a+deep+learning+to+identify+file+typeshttps://wiki.offsecml.com/Defensive+ML/Detecting+Malicious+Network+Traffic/Using+pcapshttps://wiki.offsecml.com/Defensive+ML/Detecting+Malicious+Network+Traffic/PCAP+Datasets/Kaggle+Datasetshttps://wiki.offsecml.com/Defensive+ML/Detecting+Malicious+Network+Traffic/PCAP+Datasets/IoT+Datasetshttps://wiki.offsecml.com/Defensive+ML/Detecting+Malicious+Models/Using+an+assessment+frameworkhttps://wiki.offsecml.com/Defensive+ML/Detecting+Malicious+Models/Using+a+serialization+scannerhttps://wiki.offsecml.com/Defensive+ML/Defending+DNNs/From+Inversion/Using+an+Inversion+Frameworkhttps://wiki.offsecml.com/Defensive+ML/Defending+LLMs/Using+control+vectors+to+modify+or+focus+LLM+behaviorhttps://wiki.offsecml.com/Defensive+ML/Defending+LLMs/Useful+Datasets/Using+a+prompt+injection+or+jailbreak+datasethttps://wiki.offsecml.com/Defensive+ML/Defending+LLMs/Useful+Datasets/Using+benign+and+toxic+datasets+to+benchmarkhttps://wiki.offsecml.com/Defensive+ML/Defending+LLMs/From+unwanted+inputs+and+outputs/Using+remapped+model+representations+aka+circuit+breakershttps://wiki.offsecml.com/Defensive+ML/Defending+LLMs/From+unwanted+inputs+and+outputs/Using+trajectory+mappinghttps://wiki.offsecml.com/Defensive+ML/Defending+LLMs/From+unwanted+inputs+and+outputs/Using+a+Finetuned+LLMhttps://wiki.offsecml.com/Defensive+ML/Defending+LLMs/From+Prompt+Injection/Using+an+LLM+based+detectorhttps://wiki.offsecml.com/Defensive+ML/Defending+LLMs/From+Prompt+Injection/Using+Prompt+Engineering+Techniqueshttps://wiki.offsecml.com/Defensive+ML/Defending+LLMs/From+Prompt+Injection/Using+Gradient+Analysis+to+detect+unsafe+promptshttps://wiki.offsecml.com/Defensive+ML/Defending+LLMs/From+Prompt+Injection/Using+Chat+Guardrailshttps://wiki.offsecml.com/Defensive+ML/Codebase+Analysis/Using+a+specialist+coding+LLMhttps://wiki.offsecml.com/Offensive+ML/C2+Automation/LLM+c2+tool+callinghttps://wiki.offsecml.com/Offensive+ML/General+Purpose+Hackbots/LLM+Interaction+Frameworks+aka+hackbotshttps://wiki.offsecml.com/Offensive+ML/Attacking+Code+Completion+Tools/Data+Extraction+from+Code+Completion+LLMhttps://wiki.offsecml.com/Offensive+ML/Application+Security/LLMs+for+automated+web+vulnerability+scanninghttps://wiki.offsecml.com/Offensive+ML/Application+Security/Preparing+webpages+for+LLM+ingestionhttps://wiki.offsecml.com/Offensive+ML/Modifying+Physical+Appearance/Using+ML+to+Face+Swap+Videohttps://wiki.offsecml.com/Defensive+ML/Defending+MCPs/Using+a++web+assembly+VMhttps://wiki.offsecml.com/Offensive+ML/Application+Security/Using+a+CNN+to+analyze+scraped+screenshotshttps://wiki.offsecml.com/Defensive+ML/Detecting+Malicious+Models/Using+a+eBPF++based+tracinghttps://wiki.offsecml.com/Defensive+ML/Detecting+Malicious+Models/Using+model+signatureshttps://wiki.offsecml.com/Defensive+ML/Defending+MCPs/Scanning+MCPs+for+malicious+behaviorhttps://wiki.offsecml.com/Defensive+ML/Defending+MCPs/Using+a+docker+container+to+sandbox+MCPshttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+an++API+Endpoint+or+Black+Box/Attacking+Agents+%26+MCPs/Using+tool+poisoninghttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+an++API+Endpoint+or+Black+Box/Attacking+Agents+%26+MCPs/Using+indirect+prompt+injectionshttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+an++API+Endpoint+or+Black+Box/Prompt+Injection/Using+matching+delineationhttps://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+an++API+Endpoint+or+Black+Box/Prompt+Injection/Using+roleplay+(wip)https://wiki.offsecml.com/Adversarial+ML/LLM+Attacks/Using+an++API+Endpoint+or+Black+Box/Prompt+Injection/Using+roleplayhttps://wiki.offsecml.com/Offensive+ML/MCPs/Offensive+MCP'shttps://wiki.offsecml.com/Defensive+ML/MCP's/Defensive+MCP'shttps://wiki.offsecml.com/Offensive+ML/Self-Contained+C2less+Malware/C2less+Malware+in+Windows