![[CFP for Current PhD scholars and early career researchers] Reviving multilateralism – Go Health Pro](https://assets.pubpub.org/dszqce38/favicon-61724872708457-01724931428186.png "[CFP for Current PhD scholars and early career researchers] Reviving multilateralism – Go Health Pro")
Workshop theme The rules-based international order appears to be crumbling, marked by fragmentation in both trade and defense. The US-China trade war and the imposition by the US administration of “reciprocal” tariffs on allies and adversaries alike have disrupted global trade. In defense, the US commitment to NATO has waned, prompting Europe to rearm, and … Read more
Apr 30, 2025Ravie LakshmananArtificial Intelligence / Email Security As the field of artificial intelligence (AI) continues to evolve at a rapid pace, new research has found how techniques that render the Model Context Protocol (MCP) susceptible to prompt injection attacks could be used to develop security tooling or identify malicious tools, according to a new … Read more
Agents using debugging tools drastically outperformed those that didn’t, but their success rate still wasn’t high enough. Credit: Microsoft Research This approach is much more successful than relying on the models as they’re usually used, but when your best case is a 48.4 percent success rate, you’re not ready for primetime. The limitations are likely … Read more
Mar 29, 2025Ravie LakshmananCybercrime / Vulnerability In what’s an instance of hacking the hackers, threat hunters have managed to infiltrate the online infrastructure associated with a ransomware group called BlackLock, uncovering crucial information about their modus operandi in the process. Resecurity said it identified a security vulnerability in the data leak site (DLS) operated by … Read more
AI agents such as OpenAI’s Operator have added more functionality than these tools had in the past and can now help attackers launch phishing campaigns. Symantec researchers explained that about a year ago, they would tell security pros that large language models (LLMs) were passive and could only help attackers create phishing materials or write … Read more