ransomware hospital — both words
"data breach" — exact phrase
malware -android — exclude a word
(apple OR microsoft) patch — either company, plus patch
ransom* — a wildcard match
Searches article titles, summaries, keywords and sources. Filters use publication dates.
31–40 of 73 articles
Best match · title matches first
Bleeping Computer
A new cybercrime tool called ErrTraffic allows threat actors to automate ClickFix attacks by generating 'fake glitches' on compromised websites to lure users into downloading payloads or following malicious instructions [...]
Dark Reading
Google has fixed a critical vulnerability that enabled attackers to add malicious instructions to common documents to exfiltrate sensitive corporate information.
Bleeping Computer
A new attack called 'CometJacking' exploits URL parameters to pass to Perplexity's Comet AI browser hidden instructions that allow access to sensitive data from connected services, like email and calendar. [...]
The Register
Trust and believe – AI models trained to see 'legal' doc as super legit Researchers at security firm Pangea have discovered yet another way to trivially trick large language models (LLMs) into ignoring their guardrails. Stick your adversarial instructions somewhere in a legal document to give them an air of unearned legitimacy – a trick familiar to lawyers the world over.…
Dark Reading
Because instructions appear to come from AI-generated content summaries and not an external source, the victim is more likely to follow them without suspicion.
Bleeping Computer
Google Gemini for Workspace can be exploited to generate email summaries that appear legitimate but include malicious instructions or warnings that direct users to phishing sites without using attachments or direct links. [...]
The Register
Now AI agents have identity, too. Here's how to handle it The rise of agentic AI systems is rewriting the rules of cybersecurity. Unlike generative AI, which relies on predefined instructions or prompts, AI agents operate autonomously, learn continuously, and act with minimal oversight. They collaborate across systems and adapt to dynamic environments. As enterprises scale their AI deployments, identity security must evolve in lockstep to preserve control, mitigate risk, and enforce trust.… Partner content
Bleeping Computer
A new campaign employing ClickFix attacks has been spotted targeting both Windows and Linux systems using instructions that make infections on either operating system possible. [...]
Bleeping Computer
OpenAI's containerized ChatGPT environment is open to limited yet extensive access to core instructions while allowing arbitrary file uploads and command execution within the isolated sandbox. [...]
The Register
'It was like watching a robot going rogue' says researcher OpenAI's language model GPT-4o can be tricked into writing exploit code by encoding the malicious instructions in hexadecimal, which allows an attacker to jump the model's built-in security guardrails and abuse the AI for evil purposes, according to 0Din researcher Marco Figueroa.…