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 11 articles
Best match · title matches first
Dark Reading
Researchers find it takes far less to manipulate a large language model's (LLM) behavior than anyone previously assumed.
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. [...]
The Hacker News
Cybersecurity researchers have discovered a novel attack technique called TokenBreak that can be used to bypass a large language model's (LLM) safety and content moderation guardrails with just a single character change. "The TokenBreak attack targets a text classification model's tokenization strategy to induce false negatives, leaving end targets vulnerable to attacks that the implemented
Bleeping Computer
A new class of supply chain attacks named 'slopsquatting' has emerged from the increased use of generative AI tools for coding and the model's tendency to "hallucinate" non-existent package names. [...]
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.…
The Hacker News
As many as 100 malicious artificial intelligence (AI)/machine learning (ML) models have been discovered in the Hugging Face platform. These include instances where loading a pickle file leads to code execution, software supply chain security firm JFrog said. "The model's payload grants the attacker a shell on the compromised machine, enabling them to gain full control over victims'
The Hacker News
OpenAI's compaction feature, which shrinks a long conversation to save space, could be turned into a way to copy a model's hidden reasoning out in plain text, security firm Xint has shown. OpenAI's reasoning models work through a problem before answering, and the service normally returns only the raw reasoning as an encrypted item the user cannot read. The method got past
The Hacker News
Cybersecurity researchers have disclosed a new technique dubbed GuardBreaker that's been put to use by a Russia-aligned threat actor known as UAC-0099 against a target in Ukraine with an aim to interfere with artificial intelligence (AI)-assisted analysis. The idea, ESET said in a series of posts on X, is to deliberately trip a large language model's (LLM) safety mechanisms and prevent its
Dark Reading
A tokenizer library file present in Hugging Face AI models can be manipulated to hijack the model's outputs and exfiltrate data.