Category: machine learning

Auto Added by WPeMatico

AIs as Trusted Third Parties

Posted on By infossl
academic papers, AI, cryptography, machine learning, Security technology, trust, Uncategorized

This is a truly fascinating paper: “Trusted Machine Learning Models Unlock Private Inference for Problems Currently Infeasible with Cryptography.” The basic idea is that AIs can act as trusted third parties: Abstract: We often interact with untrusted parties. Prioritization of privacy can limit the effectiveness of these interactions, as achieving certain goals necessitates sharing private … Read More “AIs as Trusted Third Parties” »

Poisoning AI Models

Posted on By infossl
academic papers, artificial intelligence, LLM, machine learning, Security technology, threat models, Uncategorized

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, reinforcement learning, and adversarial training. After this, they checked if the AI still had hidden behaviors. They found that with specific prompts, the AI could still generate exploitable … Read More “Poisoning AI Models” »

Extracting GPT’s Training Data

Posted on By infossl
academic papers, artificial intelligence, ChatGPT, cyberattack, machine learning, Security technology, Uncategorized

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 (abridged) example above, the model emits a real email address and phone number of some unsuspecting entity. This happens … Read More “Extracting GPT’s Training Data” »

Bots Are Better than Humans at Solving CAPTCHAs

Posted on By infossl
academic papers, captchas, machine learning, Security technology, Uncategorized

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 years, as their use grew, techniques to defeat or bypass CAPTCHAS have continued to improve. Meanwhile, CAPTCHAS have also evolved in terms of sophistication and diversity, … Read More “Bots Are Better than Humans at Solving CAPTCHAs” »

Using Machine Learning to Detect Keystrokes

Posted on By infossl
machine learning, Security technology, side-channel attacks, smartphones, Uncategorized

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 deep learning, the ubiquity of microphones and the rise in online services via personal devices, acoustic side channel attacks present a greater threat to keyboards than … Read More “Using Machine Learning to Detect Keystrokes” »

Indirect Instruction Injection in Multi-Modal LLMs

Posted on By infossl
academic papers, artificial intelligence, LLM, machine learning, Security technology, Uncategorized

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 instruction injection in multi-modal LLMs. An attacker generates an adversarial perturbation corresponding to the prompt and blends it into an image or audio recording. When the user asks … Read More “Indirect Instruction Injection in Multi-Modal LLMs” »

Security Risks of AI

Posted on By infossl
artificial intelligence, cybersecurity, machine learning, reports, risks, Security technology, Uncategorized

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, wrote a blog post on the report: As a first step, our report recommends the inclusion of AI security concerns within the cybersecurity programs … Read More “Security Risks of AI” »

Using LLMs to Create Bioweapons

Posted on By infossl
academic papers, artificial intelligence, biological warfare, machine learning, Security technology, Uncategorized

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. Specifically, the dual-use application of models for predicting cytotoxicity18 to create new poisons or employing AlphaFold2 to develop novel bioweapons has raised alarm. … Read More “Using LLMs to Create Bioweapons” »