Bias Amplification in RAG: Poisoning Knowledge Retrieval to Steer LLMs

In Large Language Models, Retrieval-Augmented Generation RAG systems can significantly enhance the performance of large language models by integrating external knowledge. However, RAG also introduces new security risks. Existing research focuses mainly on how poisoning attacks in RAG systems affe...

kernel security update

4.18.0-553.56.110.OL8 - Update Oracle Linux certificates Kevin Lyons - Disable signing for aarch64 Ilya Okomin - Oracle Linux RHCK Module Signing Key was added to the kernel trusted keys list olkmodsigningkey.pem Orabug: 29539237 - Update x509.genkey Orabug: 24817676 - Conflict with shim-ia32 and...

LLM Unlearning Should Be Form-Independent

Large Language Model LLM unlearning aims to erase or suppress undesirable knowledge within the model, offering promise for controlling harmful or private information to prevent misuse. However, recent studies highlight its limited efficacy in real-world scenarios, hindering practical adoption. In...

Exploiting Inaccurate Branch History in Side-Channel Attacks

Modern out-of-order CPUs heavily rely on speculative execution for performance optimization, with branch prediction serving as a cornerstone to minimize stalls and maximize efficiency. Whenever shared branch prediction resources lack proper isolation and sanitization methods, they may originate...

The Scales of Justitia: a Comprehensive Survey on Safety Evaluation of LLMs

With the rapid advancement of artificial intelligence technology, Large Language Models LLMs have demonstrated remarkable potential in the field of Natural Language Processing NLP, including areas such as content generation, human-computer interaction, machine translation, and code generation,...

EarthOL: a Proof-Of-Human-Contribution Consensus Protocol -- Addressing Fundamental Challenges in Decentralized Value Assessment with Enhanced Verification and Security Mechanisms

This paper introduces EarthOL, a novel consensus protocol that attempts to replace computational waste in blockchain systems with verifiable human contributions within bounded domains. While recognizing the fundamental impossibility of universal value assessment, we propose a domain-restricted...

Private Statistical Estimation Via Truncation

We introduce a novel framework for differentially private DP statistical estimation via data truncation, addressing a key challenge in DP estimation when the data support is unbounded. Traditional approaches rely on problem-specific sensitivity analysis, limiting their applicability. By leveragin...

The IT help desk kindly requests you read this newsletter

Welcome to this week's edition of the Threat Source newsletter. Authority bias is one of the many things that shape how we think. Taking the advice of someone with recognized authority is often far easier and usually leads to a better outcome than spending time and effort in researching the...

Building Trustworthy Multimodal AI: a Review of Fairness, Transparency, and Ethics in Vision-Language Tasks

Objective: This review explores the trustworthiness of multimodal artificial intelligence AI systems, specifically focusing on vision-language tasks. It addresses critical challenges related to fairness, transparency, and ethical implications in these systems, providing a comparative analysis of...

Mitigating the Structural Bias in Graph Adversarial Defenses

In recent years, graph neural networks GNNs have shown great potential in addressing various graph structure-related downstream tasks. However, recent studies have found that current GNNs are susceptible to malicious adversarial attacks. Given the inevitable presence of adversarial attacks in the...

A Case Study on the Use of Representativeness Bias As a Defense against Adversarial Cyber Threats

Cyberspace is an ever-evolving battleground involving adversaries seeking to circumvent existing safeguards and defenders aiming to stay one step ahead by predicting and mitigating the next threat. Existing mitigation strategies have focused primarily on solutions that consider software or hardwa...

AiXamine: Simplified LLM Safety and Security

Evaluating Large Language Models LLMs for safety and security remains a complex task, often requiring users to navigate a fragmented landscape of ad hoc benchmarks, datasets, metrics, and reporting formats. To address this challenge, we present aiXamine, a comprehensive black-box evaluation...

Is Security Human Factors Research Skewed Towards Western Ideas and Habits?

Really interesting research: "How WEIRD is Usable Privacy and Security Research?" by Ayako A. Hasegawa Daisuke Inoue, and Mitsuaki Akiyama: Abstract : In human factor fields such as human-computer interaction HCI and psychology, researchers have been concerned that participants mostly come from...

CVE-2024-1544

...

Algorithms Are Coming for Democracy—but It’s Not All Bad

In 2025, AI is poised to change every aspect of democratic politics--but it won't necessarily be for the worse. India's prime minister, Narendra Modi, has used AI to translate his speeches for his multilingual electorate in real time, demonstrating how AI can help diverse democracies to be more...

Sharks has a Bias of Polynomial Coefficients in Secret Sharing

Affected versions of this crate allowed for a bias when generating random polynomials for Shamir Secret Sharing, where instead of being within the range 0, 255 they were instead in the range 1, 255. A description from Cure53, who originally found the issue, is available: The correct method to...

Bias of Polynomial Coefficients in Secret Sharing

Affected versions of this crate allowed for a bias when generating random polynomials for Shamir Secret Sharing, where instead of being within the range 0, 255 they were instead in the range 1, 255. A description from Cure53, who originally found the issue, is available: The correct method to...

RUSTSEC-2024-0398 Bias of Polynomial Coefficients in Secret Sharing

Affected versions of this crate allowed for a bias when generating random polynomials for Shamir Secret Sharing, where instead of being within the range 0, 255 they were instead in the range 1, 255. A description from Cure53, who originally found the issue, is available: The correct method to...

Snapchat wants to put your AI-generated face in its ads

Snapchat is reserving the right to use your selfie images to power Cameos, Generative AI, and other experiences on Snapchat, including ads, according to our friends at 404 Media, The Snapchat Support page about its My Selfie feature says: “You’ll take selfies with your Snap camera or select image...

DEBIAN-CVE-2024-1544

Generating the ECDSA nonce k samples a random number r and then truncates this randomness with a modular reduction mod n where n is the order of the elliptic curve. Meaning k = r mod n. The division used during the reduction estimates a factor qe by dividing the upper two digits a digit having e....