Cyber AI Lab updateshttps://cyber-ai.co.il/Research, stories, and progress from Cyber AI Lab.Inference Attacks and Defenses on LLM-Powered Phishing Email Detection SystemsFrederik Sherman and Yoni Birman study inference attacks and defenses for LLM-powered phishing email detection. The paper is available through the HumSec 2026 workshop.https://cyber-ai.co.il/publications/phishing-inference-humsec/https://cyber-ai.co.il/publications/phishing-inference-humsec/Fri, 18 Sep 2026 12:00:00 GMTAdvPIIBench - The Adversarial Collapse of PII Detection in LLM InteractionsRoei Arpaly and Yoni Birman investigate how adversarial prompts challenge the detection of personally identifiable information in LLM interactions.https://cyber-ai.co.il/publications/advpiibench-usenix-poster/https://cyber-ai.co.il/publications/advpiibench-usenix-poster/Wed, 12 Aug 2026 12:00:00 GMTInference Attacks and Defenses on LLM-Powered Email Phishing Detection SystemsFrederik Sherman and Yoni Birman explore attacks and defenses involving LLM-powered phishing detection, presented at the USENIX Security 2026 poster session.https://cyber-ai.co.il/publications/phishing-inference-usenix-poster/https://cyber-ai.co.il/publications/phishing-inference-usenix-poster/Wed, 12 Aug 2026 12:00:00 GMTBreaking and Defending LLM-Powered Social Media Bot Detection SystemsA study of attacks and defences for language-model systems that identify social media bots.https://cyber-ai.co.il/publications/llm-bot-detection-journal/https://cyber-ai.co.il/publications/llm-bot-detection-journal/Tue, 11 Aug 2026 12:00:00 GMTPoster: Breaking and Defending LLM-Powered Social Media Bot Detection SystemsAn IEEE Symposium on Security and Privacy 2026 poster on adversarial attacks and ensemble defences for LLM-based bot detection.https://cyber-ai.co.il/publications/llm-bot-detection-poster/https://cyber-ai.co.il/publications/llm-bot-detection-poster/