Results for “"ascii"”
1–10 of 10 articles
Best match · title matches first
The Register
2 months ago
ASCII smuggling isn't just an AI security risk
Phishers find a new use for invisible Unicode tag characters
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 10 articles
Best match · title matches first
The Register
Phishers find a new use for invisible Unicode tag characters
Bleeping Computer
Google's AI assistant Gemini is vulnerable to ASCII smuggling, a well-documented attack method that could trick it into providing users with fake information, alter the model's behavior, and silently poison its data. [...]
Bleeping Computer
Google has decided not to fix a new ASCII smuggling attack in Gemini that could be used to trick the AI assistant into providing users with fake information, alter the model's behavior, and silently poison its data. [...]
Graham Cluley
In episode 22 of "The AI Fix", our hosts encounter a bowl of buttermilk king crab ice cream prepared by a baby hippo, a TV station finds an even better way to generate programme ideas than using a tank full of manatees, and Elon Musk does the world's most expensive Blade Runner cosplay. Graham discovers a robot tongue and ponders the implications of AIs with an appetite, and Mark explains ASCII smuggling — a prompt injection attack that uses completely invisible characters. All this and much more is discussed in the latest edition of "The AI Fix" podcast by Graham Cluley and Mark Stockley.
The Hacker News
Details have emerged about a now-patched vulnerability in Microsoft 365 Copilot that could enable the theft of sensitive user information using a technique called ASCII smuggling. "ASCII Smuggling is a novel technique that uses special Unicode characters that mirror ASCII but are actually not visible in the user interface," security researcher Johann Rehberger said. "This means that an attacker
Bleeping Computer
Threat actors have adopted the ASCII smuggling technique in phishing campaigns, using invisible Unicode characters to evade email security filters. [...]
The Register
Prompt injection, ASCII smuggling, and other swashbuckling attacks on the horizon Microsoft has fixed flaws in Copilot that allowed attackers to steal users' emails and other personal data by chaining together a series of LLM-specific attacks, beginning with prompt injection.…
The Register
Because apps talking like pirates and creating ASCII art never gets old Despite worries about criminals using prompt injection to trick large language models (LLMs) into leaking sensitive data or performing other destructive actions, most of these types of AI shenanigans come from job seekers trying to get their resumes past automated HR screeners – and people protesting generative AI for various reasons, according to Russian security biz Kaspersky.…
The Register
'Ignore previous instructions' thwarts Prompt-Guard model if you just add some good ol' ASCII code 32 Meta's machine-learning model for detecting prompt injection attacks – special prompts to make neural networks behave inappropriately – is itself vulnerable to, you guessed it, prompt injection attacks.…
ThreatPost
It's a double-extortion play that uses the command-line password ‘KissMe’ to hide its nasty acts and adorns its ransom note with cutesy ASCII bunny art.