Tagged:

5 posts

• Crescendo: Why Single-Turn Safety Filters Are Insufficient

  Crescendo attacks build harmful requests across individually benign turns, bypassing single-turn safety filters. Here's the mechanism, detection challenges, and defenses.

  Jul 11, 2026 jailbreak red-teaming security evaluation llm-security

• LLM Security Monitoring in Production: Anomaly Detection, Audit Logging, and Intrusion Detection for AI Systems

  Guardrails block known bad inputs. Incident response handles breaches after they happen. This post covers the gap: building LLM-specific observability that detects attacks while they are occurring — anomalous outputs, prompt injection signatures, unusual tool-call patterns, and model drift from baseline.

  Jul 10, 2026 monitoring anomaly-detection audit-logging intrusion-detection observability langfuse arize owasp nist security llm production

• Model Hub Supply Chain Attacks: Malicious Models, Tokenizer Exploits, and Typosquatting on Hugging Face

  Downloading an open-weight model from a public hub is not a read-only operation. Custom tokenizer classes and auto_map configs execute arbitrary Python when trust_remote_code is set, LoRA adapters can trojanize safe base models, and typosquatted namespaces are a documented distribution vector. Here's the threat model practitioners need before they run from_pretrained().

  Jul 9, 2026 supply-chain model-security ai-security security data-poisoning pickling fine-tuning threat-modeling

• Zero-Trust Architecture for AI Agent Deployments: Never Trust, Always Verify — Even Your Own Agents

  Zero-trust was designed for human users on networks. AI agents break its assumptions: they act autonomously, spawn child agents, inherit permissions, and run long-lived sessions. Here's how to adapt zero-trust principles specifically for multi-agent and LLM deployment contexts.

  Jul 6, 2026 zero-trust agent-security identity authentication microsegmentation spiffe nist architecture security ai-agents llm

• LLM Output Watermarking: Provenance, Detection Limits, and Evasion

  Token-level watermarks, cryptographic signing, and semantic embedding all promise attribution of AI-generated text — but paraphrase attacks, closed-pipeline requirements, and research-stage maturity constrain what any of them can actually guarantee. An honest practitioner's assessment.

  Jun 30, 2026 security llm deployment