AI and Cybersecurity research, talk and blog in-depth articleshttps://elie.nethttps://elie.net/favicon/favicon.svghttps://elie.net/favicon/favicon.svg0099ffhttps://elie.net/publication/droidcct-cryptographic-compliance-test-via-trillion-scale-measurementhttps://elie.net/publication/droidcct-cryptographic-compliance-test-via-trillion-scale-measurementThis paper presents DroidCCT, a distributed framework for large-scale cryptographic compliance testing in the Android ecosystem, analyzing trillions of cryptographic operation samples from over half a billion devices to identify implementation weaknesses and bugs.Sat, 31 Jan 2026 00:00:00 GMThttps://elie.net/talk/timeline-analysis-in-timesketch-with-sec-geminihttps://elie.net/talk/timeline-analysis-in-timesketch-with-sec-geminiThis talk discuss the TimeSketch AI Panel UI was iteratively designed to make it actionable.Fri, 08 Aug 2025 09:00:00 GMThttps://elie.net/talk/facade-high-precision-insider-threat-detection-using-contrastive-learninghttps://elie.net/talk/facade-high-precision-insider-threat-detection-using-contrastive-learningThis talk presents FACADE, a novel self-supervised AI system used by Google to detect insider threats with high precision. FACADE uses a contrastive learning strategy trained solely on benign data, achieving a false positive rate below 0.01%.Thu, 07 Aug 2025 09:00:00 GMThttps://elie.net/talk/autonomous-timeline-analysis-and-threat-hunting-an-ai-agent-for-timesketchhttps://elie.net/talk/autonomous-timeline-analysis-and-threat-hunting-an-ai-agent-for-timesketchThis talk introduces the Sec-Gemini digital forensic agent that is able to automously perform timeline analysis and threat hunting with high accuracy on real-world compromised systems and direclty integrate with TimeSketch.Wed, 06 Aug 2025 09:00:00 GMThttps://elie.net/talk/toward-secure-trustworthy-ai-independent-benchmarkinghttps://elie.net/talk/toward-secure-trustworthy-ai-independent-benchmarkingThis talk announce the open-source release of the Phare Benchmark, an independent multi-lingual security and safety benchmark for large models alongside LMEval, a large model evaluation frameworkWed, 02 Apr 2025 07:00:00 GMThttps://elie.net/talk/ai-for-cybersecurity-get-started-todayhttps://elie.net/talk/ai-for-cybersecurity-get-started-todayThis talk examine current real-world examples of AI-driven attacks and explore which defensive AI capabilities are available today.Thu, 10 Oct 2024 07:00:00 GMThttps://elie.net/talk/ai-security-top-5-recommendationshttps://elie.net/talk/ai-security-top-5-recommendationsStart securing your AI workflows against risks such as PII leaks, hallucinations, and prompt injection using our top 5 recommendations.Thu, 10 Oct 2024 07:00:00 GMThttps://elie.net/publication/generalized-power-attacks-against-crypto-hardware-using-long-range-deep-learninghttps://elie.net/publication/generalized-power-attacks-against-crypto-hardware-using-long-range-deep-learningWe present GPAM the first side-channel attack model that generalizes across multiple cryptographic algorithms, implementations, and side-channel countermeasures without the need for manual tuning or trace preprocessingThu, 05 Sep 2024 00:00:00 GMThttps://elie.net/publication/leveraging-virtual-reality-to-enhance-diversity-and-inclusion-training-at-googlehttps://elie.net/publication/leveraging-virtual-reality-to-enhance-diversity-and-inclusion-training-at-googleThis case-study explores the effectiveness of virtual reality (VR) for diversity, equity, and inclusion (DEI) training through the lens of a custom VR application developped to train Google employees."Thu, 06 Jun 2024 00:00:00 GMThttps://elie.net/blog/ai/wingardium-trivia-osa-on-device-sorting-hatbot-powered-by-gemma-ollama-usearch-and-retsimhttps://elie.net/blog/ai/wingardium-trivia-osa-on-device-sorting-hatbot-powered-by-gemma-ollama-usearch-and-retsimHow to build an accurate on-device RAG LLM system using Gemma, Ollama, USearch, and RETSim to answer questions about the characters of The Wizarding World of Harry Potter.Fri, 17 May 2024 15:00:00 GMT