35 个 · 按相关度排序
Detect model stealing, model inversion, and membership inference performed through inference-API abuse by monitoring query patterns, applying output perturbation, and red-teaming your own model's extractability.
中文简介正在准备中。当前显示原文说明。
Identify poisoned training data and backdoored models across the ML pipeline.
中文简介正在准备中。当前显示原文说明。
Deploy Llama Guard, NeMo Guardrails, and LLM Guard input/output scanners as runtime defenses.
中文简介正在准备中。当前显示原文说明。
Wire Promptfoo and DeepTeam into CI/CD for automated regression red-teaming of LLM apps against OWASP LLM Top 10 and OWASP Agentic presets, failing the build when jailbreak or injection vulnerabilities regress.
中文简介正在准备中。当前显示原文说明。
Scan Model Context Protocol servers and tool metadata for poisoning, SSRF, and unauthenticated exposure.
中文简介正在准备中。当前显示原文说明。
Test vector stores for embedding inversion, cross-tenant leakage, and poisoning.
中文简介正在准备中。当前显示原文说明。
Harden AI/LLM deployments against prompt injection, data exfiltration, model theft, and supply chain attacks.
中文简介正在准备中。当前显示原文说明。
Implements input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs. Builds a security validation pipeline using NVIDIA NeMo Guardrails Colang definitions, custom Python validators for PII Tespit and content policy enforcement, and the Guardrails AI framework for structured output validation. The guardrails system intercepts both user inputs (blocking injection attempts, stripping PII, ...
中文简介正在准备中。当前显示原文说明。
tespit etme (s) prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The tespit etme (or) analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-...
中文简介正在准备中。当前显示原文说明。
Comprehensive LLM security testing: bias detection, data leakage, prompt injection, jailbreak, alignment testing, adversarial prompts
中文简介正在准备中。当前显示原文说明。
AI/LLM security offensive checklist: prompt injection, jailbreaking, model extraction, training data poisoning, adversarial inputs, LLM-assisted attack automation, and AI system reconnaissance. Use when assessing AI/ML systems, red-teaming LLMs, or researching AI attack vectors.
中文简介正在准备中。当前显示原文说明。