What if there was a way to sneak malicious instructions into Claude, Copilot, or other top-name AI chatbots and get confidential data out of them by using characters large language models can recognize and their human users can’t? As it turns out, there was—and in some cases …
Experiments in unredacting text that has been pixelated. [...]
The Washington Post is reporting on a hack to fool automatic resume sorting programs: putting text in a white font. The idea is that the programs rely primarily on simple pattern matching, and the trick is to copy a list of relevant keywords—or the published job description—into …
New research suggests that AIs can produce perfectly secure steganographic images: Abstract: Steganography is the practice of encoding secret information into innocuous content in such a manner that an adversarial third party would not realize that there is hidden meaning. While this problem has classically been studied in security …
From an article about Zheng Xiaoqing, an American convicted of spying for China: According to a Department of Justice (DOJ) indictment, the US citizen hid confidential files stolen from his employers in the binary code of a digital photograph of a sunset, which Mr Zheng then mailed to himself …
Really interesting research demonstrating how to hide vulnerabilities in source code by manipulating how Unicode text is displayed. It’s really clever, and not the sort of attack one would normally think about. From Ross Anderson’s blog : We have discovered ways of manipulating the encoding of source code …
NASA made an oblique reference to a coded message in the color pattern of the Perseverance Mars Lander ‘s parachute. More information. [...]