Quantcast
Channel: machine learning – Schneier on Security
Browsing all 12 articles
Browse latest View live

Attacking Machine Learning Systems

The field of machine learning (ML) security—and corresponding adversarial ML—is rapidly advancing as researchers develop sophisticated techniques to perturb, disrupt, or steal the ML model or data....

View Article


Putting Undetectable Backdoors in Machine Learning Models

This is really interesting research from a few months ago: Abstract: Given the computational cost and technical expertise required to train machine learning models, users may delegate the task of...

View Article

Side-Channel Attack against CRYSTALS-Kyber

CRYSTALS-Kyber is one of the public-key algorithms currently recommended by NIST as part of its post-quantum cryptography standardization process. Researchers have just published a side-channel...

View Article

LLMs and Phishing

Here’s an experiment being run by undergraduate computer science students everywhere: Ask ChatGPT to generate phishing emails, and test whether these are better at persuading victims to respond or...

View Article

Using LLMs to Create Bioweapons

I’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 for harmful purposes....

View Article


Security Risks of AI

Stanford 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 workshop organizers,...

View Article

Indirect Instruction Injection in Multi-Modal LLMs

Interesting 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...

View Article

Using Machine Learning to Detect Keystrokes

Researchers 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...

View Article


Bots Are Better than Humans at Solving CAPTCHAs

Interesting 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...

View Article


Extracting GPT’s Training Data

This 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 model responds (complete transcript here). In the...

View Article

Poisoning AI Models

New 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,...

View Article

Using LLMs to Unredact Text

Initial 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.

View Article
Browsing all 12 articles
Browse latest View live