Reverse Prompt Engineering in Generative AI: A Baseline for Deepfake, Deception and Disinformation Mitigation

PyRIT: Democratizing AI Red Teaming Through Open-Source Tooling

Semantic Isomorphism Attacks and Defense Evaluation for Jailbreaking Large Language Models

The safety alignment of large language models (LLMs) faces persistent challenges from jailbreak attacks. While existing methods mostly leverage prompt engineering or adversarial optimization, we identify and formalize an underexplored semantic isomorphism vulnerability where harmful and safe scenarios share highly cons...

Decoding Guardrails: XAI-Guided Perturbation Analysis of Prompt Injection Detection

An exploratory case study that applies explainable artificial intelligence techniques to analyze how Prompt Guard 2 distinguishes malicious from benign prompts finds that Prompt Guard 2's decisions rely on the cumulative contribution of many tokens rather than a few dominant ones, yet saliency-guided synonym substituti...

Prompt Pipelines as Engineered Artifacts: Regression-Testing a Multi-agent Threat-Modeling Pipeline

The experience suggests that the PromptOps practices recently proposed for general LLM applications transfer directly to security engineering, and that a fixed evaluation corpus with cost-aware metrics is the single most valuable artifact a prompt-pipeline team can maintain.

REPRO: Reflective Evolutionary Prompt Optimizer for Automated LLM Red-Teaming

Safety-aligned large language models (LLMs) remain vulnerable to adversarial prompts that bypass their safety training. Existing automated red-teaming methods either require privileged access unavailable in production, rely on manually engineered per-model templates, or optimize a single objective without population-le...

RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents

Tool-using language-model agents are vulnerable to indirect prompt injection because they must act on untrusted external content. Existing training-time defenses can reduce attack success rates, but often at the cost of general capabilities. We show that training-based defenses induce substantial drift in the model's o...