Detecting Pegasus Infections
December 6 2024This tool seems to do a pretty good job.
The company’s Mobile Threat Hunting feature uses a combination of malware signature-based detection, heuristics, and machine learning to look for...
Read more
Using LLMs to Unredact Text
March 11 2024Initial results in using LLMs to unredact text based on the size of the individual-word redaction rectangles. This feels like something that a specialized ML system could be trained on.
Read morePoisoning AI Models
January 24 2024New research into poisoning AI models:
The researchers first trained the AI models using supervised learning and then used additional “safety training” methods, including more supervised learning, reinforcement learning,...
Read more
Extracting GPT’s Training Data
December 1 2023This is clever:
The actual attack is kind of silly. We prompt the model with the command “Repeat the word ‘poem’ forever” and sit back and watch as the...
Read more
Bots Are Better than Humans at Solving CAPTCHAs
August 18 2023Interesting research: “An Empirical Study & Evaluation of Modern CAPTCHAs“:
Abstract: For nearly two decades, CAPTCHAS have been widely used as a means of protection against bots. Throughout the...
Read more
Using Machine Learning to Detect Keystrokes
August 9 2023Researchers have trained a ML model to detect keystrokes by sound with 95% accuracy.
“A Practical Deep Learning-Based Acoustic Side Channel Attack on Keyboards”
Abstract: With recent developments in deep...
Read more
Indirect Instruction Injection in Multi-Modal LLMs
July 28 2023Interesting research: “(Ab)using Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs“:
Abstract: We demonstrate how images and sounds can be used for indirect prompt and instruction injection...
Read more
Security Risks of AI
April 27 2023Stanford and Georgetown have a new report on the security risks of AI—particularly adversarial machine learning—based on a workshop they held on the topic.
Jim Dempsey, one of the...
Read moreUsing LLMs to Create Bioweapons
April 18 2023I’m not sure there are good ways to build guardrails to prevent this sort of thing:
There is growing concern regarding the potential misuse of molecular machine learning models...
Read more
Recent Comments