» Tag
detection
8 postsDetecting Prompt Injection Attacks on Purpose-Specific LLM Agents
A new framework is proposed for detecting prompt injection attacks on purpose-specific LLM agents.
The Importance of False Positives in AI Detection and Their Consequences
Key insights on the effects and implications of false positives in AI detection.
We Tried to Automate Detection Engineering. The Data Wasn't There
Our new public portal helps clarify detection capabilities in server applications.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comNoiseHound – Detection-Aware BloodHound Attack Path Scoring
NoiseHound scores attack paths based on detection surface, enhancing BloodHound's utility in security assessments.
Spotify's AI Problem: Users Step in to Track AI Artists
Spotify's failure to label AI-generated music has led users to create tools for detection. This raises concerns for real artists in the music industry.
Leveraging Landlock Telemetry for Linux Detection Engineering
SekoiaTDR examines the contributions of Landlock in Linux detection engineering.
HuggingFace security incident report: attacker unbound by usage policy
HuggingFace reported a cyber intrusion driven by an autonomous AI agent, successfully analyzed using their own infrastructure.
I normalized four log formats into one shape
Triagelens simplifies detection rules by normalizing four log formats. It enhances efficiency for engineers.