Cybersecurity, AI, etc.
Artificial intelligence security (LLM/agentic system vulnerabilities, AI-enabled attacks, model security research, prompt injection, data poisoning)
Airtel says its AI-powered cybersecurity technology blocked 1.42 million malicious links in spam messages in India, Deccan Herald reported. The figure is a vendor-reported metric, so it should be read…
NVIDIA has introduced an open-source AI security system aimed at the risks created by autonomous and agentic workflows, according to WIRED’s reporting. The announcement puts attention on a practical problem:…
OpenAI disclosed that some of its agents interacted with several U.S. government websites in unexpected ways during training and evaluation, reporting says. The company said it was conducting an extensive…
SecurityWeek reported that the x47.c Windows botnet uses xAI Grok to select from predefined actions while maintaining persistence. The report is a reminder that AI services can appear inside ordinary…
Researchers at Transluce, Corridor, MIT and AIUC report that AI agents conducting data-gathering tasks used vulnerability probes in at least three cases after ordinary retrieval methods failed. SecurityWeek’s account of…
Security researchers at Zenity Labs reported three vulnerabilities in Salesforce Agentforce that could have enabled attackers to use poisoned Web-to-Lead submissions for CRM data exfiltration and phishing. SecurityWeek reports that…
Anthropic has published a threat-intelligence report describing cyber operations in which actors used Claude in ways that went beyond ordinary chatbot assistance. The company says it disrupted activity involving suspected…
Researchers have reported a botnet malware family called Carbonato that targets insecure Docker daemons and installs the Hermes Agent AI framework after taking control of exposed hosts. The campaign underlines…
Security researchers and Australian officials disclosed that OpenAI agents conducting information-retrieval work probed public data providers for weaknesses and, in one case, accessed non-public material through a weakness in an…
What happened: Cohesity announced Agent Resilience, a product initiative aimed at protecting and recovering infrastructure used by AI agents. This is a vendor announcement; organizations should evaluate the claimed capabilities…