The AI worm, tested on an isolated 33-host network, demonstrated a significant ability to adapt and exploit.
Tag: tested
AI, Global Security News, Network Security
Researchers Build Self-Replicating AI Worm That Operates Entirely on Local, Open-Weight Models
University of Toronto researchers have built and tested a proof-of-concept AI-driven computer worm that uses a locally hosted open-weight large language model to reason its way through a network, generate tailored attack strategies for each target it encounters, and replicate itself, all without human intervention and without touching a commercial AI service. The preprint, posted…
AI, Exploits, Global Security News, Network Security
Autonomous AI-driven worm can reason its way through corporate networks
Researchers at the University of Toronto, the Vector Institute, and the University of Cambridge have built and tested a proof-of-concept AI-driven worm that does not operate on a fixed list of exploits. Instead, it analyzes each target it encounters, reasons about how to attack it, and creates a strategy on the fly, all with the…
AI, Apps, Europe, Global Security News, Risk Management
Multi-Turn Attacks Expose Ongoing Weaknesses Across Frontier AI Models
A Cisco evaluation of frontier LLMs found that no tested model consistently resisted multi-turn adversarial attacks, raising concerns about current AI safety assessments. The research suggests that many widely used AI safety benchmarks may underestimate real-world risk because they focus primarily on single-turn prompt evaluations rather than adaptive, iterative attacks. Key Takeaways from Cisco’s Research…
AI, Apps, Compliance, Global Security News, Risk Management
Agentic AI and the Evolution of Code Security in Modern Development
The rise of agentic artificial intelligence (AI) is fundamentally reshaping how software is developed, tested, and secured. In a recent discussion with Jeremy Katz, VP of Code Security at Sonar, key insights emerged about how AI-driven workflows are accelerating development while introducing new security challenges that organizations must address. Agentic Workflows in Modern Development Agentic…
AI, Cybersecurity, Global Security News
Claude Mythos finds 271 Firefox flaws, Mozilla believes zero-days are numbered
The Mozilla Foundation tested Claude Mythos, an Anthropic AI model that has stirred debate in the cybersecurity community. Before granting access to Mythos, Mozilla scanned Firefox using Opus 4.6, which led to fixes for 22 security-sensitive bugs in Firefox 148. For instance, Mythos identified 271 vulnerabilities in Firefox 150. Firefox CTO Bobby Holley said other…
AI, Global Security News
GitHub Copilot CLI gets a second-opinion feature built on cross-model review
Coding agents make decisions in sequence: a plan is drafted, implemented, then tested. Any error introduced early compounds as subsequent steps build on the same flawed assumption. Self-reflection is a recognized mitigation technique, and one GitHub Copilot already supports, but a model reviewing its own output is still constrained by the same training data and…
AI, Cybersecurity, Global Security News
AI in the SOC: What Could Go Wrong?
Two cybersecurity leaders tested out AI in their respective SOCs for six months — and here’s what they learned.
AI, Global Security News, Government & Policy, Risk Management
Fulton County lawsuit claims feds used ‘gross mischaracterizations’ to justify raid
A former federal official who tested and certified voting machines used in Fulton County, Georgia for the 2020 presidential election told a court that the federal government misrepresented key facts and omitted exculpatory public evidence while seeking a warrant in last month’s law enforcement raid. The raid, carried out by the FBI and overseen by…