Results for “"tricked"”
1–10 of 79 articles
Best match · title matches first
The Register
25 days ago
Jev and other decision models can still be tricked with prompt injection
Never making type errors does not mean never making errors
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.
1–10 of 79 articles
Best match · title matches first
The Register
Never making type errors does not mean never making errors
The Register
More prompt-injection hijinks from wunderwuzzi
Dark Reading
Researchers discovered a "meta-hacking" technique that can manipulate the AI service into revealing its own security weaknesses.
The Register
How to social engineer an AI's reasoning engine
The Hacker News
Attacker-controlled instructions can make Atlassian's Rovo assistant collect Jira or Confluence data that a signed-in user can access, then send it to an outside server. Two security firms found that behavior independently, by different routes. Only one of those routes is confirmed closed. PromptArmor, an AI security firm, hid the instructions in content Rovo reads. It said an uploaded file was
The Hacker News
Ask an AI coding agent to scan open-source code for security holes, and it might run the attacker's code on your own machine instead. That is the finding in a proof-of-concept published Wednesday by the AI Now Institute, an attack it calls "Friendly Fire." It works against Anthropic's Claude Code and OpenAI's Codex when either is running in an autonomous mode that approves its own
The Register
If you want a picture of the future of LLM security, imagine Whac-a-Mole meets Groundhog Day
The Register
Wash your mouth out with digital soap Apple Intelligence, the personal AI system integrated into newer Macs, iPhones, and other iThings, can be hijacked using prompt injection, forcing the model into producing an attacker-controlled result and putting millions of users at risk, researchers have shown.…
Bleeping Computer
Using only natural language instructions, researchers were able to bypass Google Gemini's defenses against malicious prompt injection and create misleading events to leak private Calendar data. [...]
The Hacker News
Malicious actors can exploit default configurations in ServiceNow's Now Assist generative artificial intelligence (AI) platform and leverage its agentic capabilities to conduct prompt injection attacks. The second-order prompt injection, according to AppOmni, makes use of Now Assist's agent-to-agent discovery to execute unauthorized actions, enabling attackers to copy and exfiltrate sensitive