BadMoE: Backdooring Mixture-Of-Experts LLMs Via Optimizing Routing Triggers and Infecting Dormant Experts

Mixture-of-Experts MoE have emerged as a powerful architecture for large language models LLMs, enabling efficient scaling of model capacity while maintaining manageable computational costs. The key advantage lies in their ability to route different tokens to different "expert'' networks within th...

AI Industry is Trying to Subvert the Definition of “Open Source AI”

The Open Source Initiative has published news article here its definition of "open source AI," and it's terrible. It allows for secret training data and mechanisms. It allows for development to be done in secret. Since for a neural network, the training data is the source code--it's how the model...

Reducing False Positives in API Security: Advanced Techniques Using Machine Learning

False positives in API security are a serious problem, often resulting in wasted results and time, missing real threats, alert fatigue, and operational disruption. Fortunately, however, emerging technologies like machine learning ML can help organizations minimize false positives and streamline t...

AI Pulse: Brazil Gets Bold with Meta, Interpol’s Red Flag & more

The second edition of AI Pulse is all about AI regulation: what’s coming, why it matters, and what might happen without it. We look at Brazil’s hard não to Meta, how communities are pushing back against AI training data use, Interpol’s warnings about AI deepfakes, and more...

Peloton accused of providing customer chat data to train AI

It seems that Peloton may have been providing more training than just for its customers, as its set to face court in California accused of using user chat data to train AI. Peloton Interactive, Inc. is a US-based exercise equipment and media company, known for its stationary bicycles, treadmills,...

SUSE CVE-2024-5206

A sensitive data leakage vulnerability was identified in scikit-learn's TfidfVectorizer, specifically in versions up to and including 1.4.1.post1, which was fixed in version 1.5.0. The vulnerability arises from the unexpected storage of all tokens present in the training data within the stopwords...

CVE-2024-5206

A sensitive data leakage vulnerability was identified in scikit-learn's TfidfVectorizer, specifically in versions up to and including 1.4.1.post1, which was fixed in version 1.5.0. The vulnerability arises from the unexpected storage of all tokens present in the training data within the stopwords...

CVE-2024-5206 Sensitive Data Leakage in sklearn.feature_extraction.text.TfidfVectorizer in scikit-learn/scikit-learn

A sensitive data leakage vulnerability was identified in scikit-learn's TfidfVectorizer, specifically in versions up to and including 1.4.1.post1, which was fixed in version 1.5.0. The vulnerability arises from the unexpected storage of all tokens present in the training data within the stopwords...

CVE-2024-5206 Sensitive Data Leakage in sklearn.feature_extraction.text.TfidfVectorizer in scikit-learn/scikit-learn

A sensitive data leakage vulnerability was identified in scikit-learn's TfidfVectorizer, specifically in versions up to and including 1.4.1.post1, which was fixed in version 1.5.0. The vulnerability arises from the unexpected storage of all tokens present in the training data within the stopwords...

scikit-learn Security Vulnerabilities

scikit-learn is an open source Python-based machine learning package that supports spam detection, image recognition, and prediction of continuous-valued attributes of associations. A security vulnerability exists in scikit-learn 1.4.1.post1 and earlier versions, which stems from accidentally...

Securing AI Development in the Cloud: Navigating the Risks and Opportunities

AI-TRiSM - Trust, Risk and Security Management in the Age of AI Co-authored by Lara Sunday and Pojan Shahrivar As artificial intelligence AI and machine learning ML technologies continue to advance and proliferate, organizations across industries are investing heavily in these transformative...

LLMs’ Data-Control Path Insecurity

Back in the 1960s, if you played a 2,600Hz tone into an AT&T pay phone, you could make calls without paying. A phone hacker named John Draper noticed that the plastic whistle that came free in a box of Captain Crunch cereal worked to make the right sound. That became his hacker name, and everyone...

HackerOne: LLM03: Training Data Poisoning via ASCII decoding

Vulnerability description not provided...

NIST Warns of Security and Privacy Risks from Rapid AI System Deployment

The U.S. National Institute of Standards and Technology NIST is calling attention to the privacy and security challenges that arise as a result of increased deployment of artificial intelligence AI systems in recent years. "These security and privacy challenges include the potential for adversari...

Information Disclosure

mltable is vulnerable to Information Disclosure. An attacker could exploit this vulnerability to disclose training data...

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 abridged example above, the model emits a real email address and phone number of some unsuspecting...

Class-Action Lawsuit for Scraping Data without Permission

I have mixed feelings about this class-action lawsuit against OpenAI and Microsoft, claiming that it "scraped 300 billion words from the internet" without either registering as a data broker or obtaining consent. On the one hand, I want this to be a protected fair use of public data. On the other...

How to keep your ChatGPT conversations out of its training data

Last week, OpenAI announced it had given ChatGPT users the option to turn off their chat history. ChatGPT is a "generative AI", a machine learning algorithm that can understand language and generate written responses. Users can interact with it by asking questions, and the conversations users hav...

I-TECH TrainSmart SQL注入漏洞

I-TECH TrainSmart is an open source web-based training data collection system from I-TECH. A security vulnerability exists in I-TECH TrainSmart version r1044 that stems from the presence of a SQL injection vulnerability...

WeBank Federated AI Technology Enabler 安全漏洞

WeBank Federated AI Technology Enabler is an industrial-grade federated learning framework. A security vulnerability exists in WeBank Federated AI Technology Enabler versions 0.1 through 1.4.2. An attacker exploited the vulnerability to read sensitive information during the training process of...