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...

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,...

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...

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...

Important: kernel-rt security update

The kernel-rt packages provide the Real Time Linux Kernel, which enables fine-tuning for systems with extremely high determinism requirements. Security Fixes: CVE-2023-6040 CVE-2024-26595 CVE-2021-46984 CVE-2023-52478 CVE-2023-52476 CVE-2023-52522 CVE-2021-47101 CVE-2021-47097 CVE-2023-52605...

ALSA-2024:7001 Important: kernel-rt security update

The kernel-rt packages provide the Real Time Linux Kernel, which enables fine-tuning for systems with extremely high determinism requirements. Security Fixes: CVE-2023-6040 CVE-2024-26595 CVE-2021-46984 CVE-2023-52478 CVE-2023-52476 CVE-2023-52522 CVE-2021-47101 CVE-2021-47097 CVE-2023-52605...

MindsDB 安全漏洞

MindsDB is an emerging low-code machine learning platform from MindsDB, Inc. A security vulnerability exists in MindsDB version 23.10.2.0 and earlier, which stems from the presence of deserialization of untrusted data, allowing a maliciously uploaded model to run arbitrary code on the server when...

Important: Red Hat Security Advisory: kernel-rt security update

An update for kernel-rt is now available for Red Hat Enterprise Linux 9.2 Extended Update Support. Red Hat Product Security has rated this update as having a security impact of Important. A Common Vulnerability Scoring System CVSS base score, which gives a detailed severity rating, is available f...

RHEL 9 : kernel-rt (RHSA-2024:4831)

The remote Redhat Enterprise Linux 9 host has packages installed that are affected by multiple vulnerabilities as referenced in the RHSA-2024:4831 advisory. The kernel-rt packages provide the Real Time Linux Kernel, which enables fine-tuning for systems with extremely high determinism requirement...

RLSA-2024:3627 Moderate: kernel-rt security and bug fix update

The kernel-rt packages provide the Real Time Linux Kernel, which enables fine-tuning for systems with extremely high determinism requirements. Security Fixes: kernel: Marvin vulnerability side-channel leakage in the RSA decryption operation CVE-2023-6240 kernel: Information disclosure in...

Important: Red Hat Security Advisory: kernel-rt security and bug fix update

An update for kernel-rt is now available for Red Hat Enterprise Linux 8.4 Advanced Mission Critical Update Support, Red Hat Enterprise Linux 8.4 Telecommunications Update Service, and Red Hat Enterprise Linux 8.4 Update Services for SAP Solutions. Red Hat Product Security has rated this update as...

Moderate: Red Hat Security Advisory: kernel-rt security and bug fix update

An update for kernel-rt is now available for Red Hat Enterprise Linux 8. Red Hat Product Security has rated this update as having a security impact of Moderate. A Common Vulnerability Scoring System CVSS base score, which gives a detailed severity rating, is available for each vulnerability from...