Threat actors can hijack machine learning (ML) models that power artificial intelligence (AI) to deploy malware and move laterally across corporate networks, researchers have found. These models, which are often publicly available, serve as a new launchpad for a range of attacks that can also poison an organization’s supply chain – and businesses need to …
Machine Learning Models: A Dangerous New Attack Vector Read More »
A major security leak has led to the creation of rogue “trusted” apps that can access the entire Android operating system on devices from Samsung, LG and others. As shared by Googler Lukasz Siewierski (Going through Mishaal Rahman), Google’s Android Partner Vulnerability Initiative (APVI) publicly disclosed a new vulnerability that affected devices from Samsung, LG, …
As the University of Idaho holds a vigil Wednesday night in remembrance of four students who were fatally stabbed in an off-campus home, the lack of a suspect or a clear motive more than two weeks later has fueled frustration with the police and resulted in amateur sleuths determined to solve the case. The hundreds …
Since then, the quest to proliferate increasingly broad linguistic patterns has accelerated, and many of the dangers we warned of, such as mass publication of hateful texts and misinformation, continue to manifest themselves. Just a few days ago, Meta released his “Galactica” LLM, which is supposed to “summarize academic papers, solve mathematical problems, generate Wiki …
Effective altruism pushes a dangerous brand of ‘AI security’ Read More »
Rob Allen, VP of Operations, ThreatLocker challenged the Computing CyberSecurity Festival audience to think about some of the software they used, such as Microsoft PowerShell, to see if that software needed to access data like only Office documents, or even if he needed to be able to talk to the Internet as a whole. This …
Good software can be as dangerous as bad, says ThreatLocker Read More »
