
CVE-2025-54794-Hijacking-Claude-AI-with-a-Prompt-Injection-The-Jailbreak-That-Talked-Back
A high-severity prompt injection flaw in Claude AI proves that even the smartest language models can be turned into weapons — all with a few lines of…

A high-severity prompt injection flaw in Claude AI proves that even the smartest language models can be turned into weapons — all with a few lines of…

A Python library for Secure and Explainable Machine Learning Documentation available @ https://secml.gitlab.io Follow us on Twitter @…

CVE-2026-54121 (Certighost) AD CS DC-impersonation PoC. Patched SAN handling + MAQ-safe account reuse.

We asked 6 AIs about their own programming. All 6 said jailbreaking will never be fixed. Run it yourself — $2, 10 minutes.

CVPR2023: Unlearnable Clusters: Towards Label-agnostic Unlearnable Examples

CEREBRO-RED v2: Advanced LLM Red Team Research Platform with PAIR Algorithm and LLM-as-a-Judge Evaluation

Reverse Shell Detection with Machine Learning

Practical black-box adversarial packet generation against encrypted traffic classification with minimal overhead and full packet recoverability.

The code for ACM MM2024 (Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning)

A prompt injection in a code‑review bot that executes AI‑generated fixes in a sandbox. The sandbox uses a blacklist to prevent dangerous commands,…

Evaluation framework that tests whether large language models follow invisible Unicode-encoded instructions embedded in normal-looking text, with…

Two-stage prompt-injection and jailbreak detector: regex gates plus a quantised DeBERTa-v3 ONNX classifier, with image, document, and audio support.…






Production AI defense with 7-layer protection: mathematical constraints, object-capability access, distributed O2 consensus, SVETILO ethics. First…