Tag

Ai Vulnerabilities

All articles tagged with #ai vulnerabilities

Mullin Blames AI for Tech Outages, Ignoring Intelligence Officials' Reassurance
politics2 hours ago

Mullin Blames AI for Tech Outages, Ignoring Intelligence Officials' Reassurance

Homeland Security Secretary Markwayne Mullin attributed recent widespread IT disruptions to artificial intelligence overwhelming legacy systems, citing a single unnamed source. This claim contradicts statements from the Director of National Intelligence and the Secretary of State, who ruled out cyberattacks and state-sponsored efforts, attributing the issues to routine patching and maintenance.

Apple Caps Bug Bounty Submissions to Curb AI-Generated Security Noise
technology3 months ago

Apple Caps Bug Bounty Submissions to Curb AI-Generated Security Noise

Apple has implemented a cap on open vulnerability reports and a 30-day cooldown period for its bug bounty program to manage a surge in AI-generated submissions. This move aims to filter out low-quality 'AI slop' that overwhelms review teams, though it has inadvertently blocked legitimate findings from some researchers. Apple is simultaneously accelerating its own patch cycle using AI tools to address the growing threat landscape.

Addressing Security and Regulatory Challenges in AI and Autonomous Agents
technology11 months ago

Addressing Security and Regulatory Challenges in AI and Autonomous Agents

An AI security researcher warns that traditional cybersecurity teams are unprepared for the unique vulnerabilities of AI systems, which can be manipulated through language and indirect instructions. He emphasizes the need for expertise in both AI security and cybersecurity to effectively address these risks, and criticizes many AI security startups for overpromising on protection. The article highlights the growing investment in AI security and the importance of developing specialized skills to manage AI-related security challenges.

Cybersecurity Risks of Hidden Commands in AI-Generated Images
technology1 year ago

Cybersecurity Risks of Hidden Commands in AI-Generated Images

Promptware, a new form of malware targeting AI and smart home devices through prompt injections, poses significant security risks by tricking AI systems into executing malicious commands. To protect against this, users should keep devices updated, avoid opening unknown messages, limit AI access to untrusted messages, disable AI features in messaging apps, and scrutinize data before copying or pasting. These practices help safeguard privacy and prevent AI manipulation in the home.

Google Gemini flaw enables email summary phishing attacks
technology1 year ago

Google Gemini flaw enables email summary phishing attacks

Google's Gemini AI in Workspace can be exploited through hidden prompt injections in emails to generate convincing phishing warnings or malicious instructions, posing security risks. Despite safeguards, attackers can embed invisible directives using HTML and CSS, which Gemini obeys when summarizing emails, potentially leading users to trust malicious content. Google is working on defenses, but users should remain cautious and not rely solely on Gemini summaries for security alerts.