Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?

Low rank adaptation LoRA has emerged as a prominent technique for fine-tuning large language models LLMs thanks to its superb efficiency gains over previous methods. While extensive studies have examined the performance and structural properties of LoRA, its behavior upon training-time attacks...

Safe Delta: Consistently Preserving Safety When Fine-Tuning LLMs on Diverse Datasets

Large language models LLMs have shown great potential as general-purpose AI assistants across various domains. To fully leverage this potential in specific applications, many companies provide fine-tuning API services, enabling users to upload their own data for LLM customization. However,...

DataSentinel: a Game-Theoretic Detection of Prompt Injection Attacks

LLM-integrated applications and agents are vulnerable to prompt injection attacks, where an attacker injects prompts into their inputs to induce attacker-desired outputs. A detection method aims to determine whether a given input is contaminated by an injected prompt. However, existing detection...

Analysing Safety Risks in LLMs Fine-Tuned with Pseudo-Malicious Cyber Security Data

The integration of large language models LLMs into cyber security applications presents significant opportunities, such as enhancing threat analysis and malware detection, but can also introduce critical risks and safety concerns, including personal data leakage and automated generation of new...

Private LoRA Fine-Tuning of Open-Source LLMs with Homomorphic Encryption

Preserving data confidentiality during the fine-tuning of open-source Large Language Models LLMs is crucial for sensitive applications. This work introduces an interactive protocol adapting the Low-Rank Adaptation LoRA technique for private fine-tuning. Homomorphic Encryption HE protects the...

Israeli NSO Group Fined $168M for Pegasus Spyware Attack on WhatsApp

US jury orders NSO Group to pay $168M to WhatsApp and Meta over Pegasus spyware use in 2019…...

The Steganographic Potentials of Language Models

The potential for large language models LLMs to hide messages within plain text steganography poses a challenge to detection and thwarting of unaligned AI agents, and undermines faithfulness of LLMs reasoning. We explore the steganographic capabilities of LLMs fine-tuned via reinforcement learnin...

LLMs' Suitability for Network Security: a Case Study of STRIDE Threat Modeling

Artificial Intelligence AI is expected to be an integral part of next-generation AI-native 6G networks. With the prevalence of AI, researchers have identified numerous use cases of AI in network security. However, there are almost nonexistent studies that analyze the suitability of Large Language...

Backdoor Attacks against Patch-Based Mixture of Experts

As Deep Neural Networks DNNs continue to require larger amounts of data and computational power, Mixture of Experts MoE models have become a popular choice to reduce computational complexity. This popularity increases the importance of considering the security of MoE architectures. Unfortunately,...

TikTok Slammed With €530 Million GDPR Fine for Sending E.U. Data to China

Ireland's Data Protection Commission DPC on Friday fined popular video-sharing platform TikTok €530 million $601 million for infringing data protection regulations in the region by transferring European users' data to China. "TikTok infringed the GDPR regarding its transfers of EEA European...

VIDSTAMP: a Temporally-Aware Watermark for Ownership and Integrity in Video Diffusion Models

The rapid rise of video diffusion models has enabled the generation of highly realistic and temporally coherent videos, raising critical concerns about content authenticity, provenance, and misuse. Existing watermarking approaches, whether passive, post-hoc, or adapted from image-based techniques...

Can Differentially Private Fine-Tuning LLMs Protect against Privacy Attacks?

Fine-tuning large language models LLMs has become an essential strategy for adapting them to specialized tasks; however, this process introduces significant privacy challenges, as sensitive training data may be inadvertently memorized and exposed. Although differential privacy DP offers strong...

[SECURITY] Fedora 41 Update: icecat-115.22.0-2.rh1.fc41

GNU IceCat is the GNU version of the Firefox ESR browser. Extensions included to this version of IceCat: LibreJS GNU LibreJS aims to address the JavaScript problem described in the article "The JavaScript Trap" of Richard Stallman. JShelter: Mitigates potential threats from JavaScript, including...

Enhancing Vulnerability Reports with Automated and Augmented Description Summarization

Public vulnerability databases, such as the National Vulnerability Database NVD, document vulnerabilities and facilitate threat information sharing. However, they often suffer from short descriptions and outdated or insufficient information. In this paper, we introduce Zad, a system designed to...

Automating Function-Level TARA for Automotive Full-Lifecycle Security

As modern vehicles evolve into intelligent and connected systems, their growing complexity introduces significant cybersecurity risks. Threat Analysis and Risk Assessment TARA has therefore become essential for managing these risks under mandatory regulations. However, existing TARA automation...

Case Study: Fine-Tuning Small Language Models for Accurate and Private CWE Detection in Python Code

Large Language Models LLMs have demonstrated significant capabilities in understanding and analyzing code for security vulnerabilities, such as Common Weakness Enumerations CWEs. However, their reliance on cloud infrastructure and substantial computational requirements pose challenges for analyzi...

Malicious code in fine-packages (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware efa7db7b7f29b44c0f53be5db51efa983975a15a5343fd0adf918ed6f7284c52 Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

A Large Language Model LLM powered GUI agent is a specialized autonomous system that performs tasks on the user's behalf according to high-level instructions. It does so by perceiving and interpreting the graphical user interfaces GUIs of relevant apps, often visually, inferring necessary sequenc...

KubeFence: Security Hardening of the Kubernetes Attack Surface

Kubernetes K8s is widely used to orchestrate containerized applications, including critical services in domains such as finance, healthcare, and government. However, its extensive and feature-rich API interface exposes a broad attack surface, making K8s vulnerable to exploits of software...

Apple Fined €150 Million by French Regulator Over Discriminatory ATT Consent Practices

Apple has been hit with a fine of €150 million $162 million by France's competition watchdog over the implementation of its App Tracking Transparency ATT privacy framework. The Autorité de la concurrence said it's imposing a financial penalty against Apple for abusing its dominant position as a...