SV-LLM: an Agentic Approach for SoC Security Verification Using Large Language Models

Ensuring the security of complex system-on-chips SoCs designs is a critical imperative, yet traditional verification techniques struggle to keep pace due to significant challenges in automation, scalability, comprehensiveness, and adaptability. The advent of large language models LLMs, with their...

Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA

Memorization in large language models LLMs makes them vulnerable to data extraction attacks. While pre-training memorization has been extensively studied, fewer works have explored its impact in fine-tuning, particularly for LoRA fine-tuning, a widely adopted parameter-efficient method. In this...

VulStamp: Vulnerability Assessment Using Large Language Model

Although modern vulnerability detection tools enable developers to efficiently identify numerous security flaws, indiscriminate remediation efforts often lead to superfluous development expenses. This is particularly true given that a substantial portion of detected vulnerabilities either possess...

QGuard:Question-Based Zero-Shot Guard for Multi-Modal LLM Safety

The recent advancements in Large Language ModelsLLMs have had a significant impact on a wide range of fields, from general domains to specialized areas. However, these advancements have also significantly increased the potential for malicious users to exploit harmful and jailbreak prompts for...

InverTune: Removing Backdoors from Multimodal Contrastive Learning Models Via Trigger Inversion and Activation Tuning

Multimodal contrastive learning models like CLIP have demonstrated remarkable vision-language alignment capabilities, yet their vulnerability to backdoor attacks poses critical security risks. Attackers can implant latent triggers that persist through downstream tasks, enabling malicious control ...

Smart Buildings Energy Consumption Forecasting Using Adaptive Evolutionary Ensemble Learning Models

Smart buildings are gaining popularity because they can enhance energy efficiency, lower costs, improve security, and provide a more comfortable and convenient environment for building occupants. A considerable portion of the global energy supply is consumed in the building sector and plays a...

MEraser: an Effective Fingerprint Erasure Approach for Large Language Models

Large Language Models LLMs have become increasingly prevalent across various sectors, raising critical concerns about model ownership and intellectual property protection. Although backdoor-based fingerprinting has emerged as a promising solution for model authentication, effective attacks for...

SecFwT: Efficient Privacy-Preserving Fine-Tuning of Large Language Models Using Forward-Only Passes

Large language models LLMs have transformed numerous fields, yet their adaptation to specialized tasks in privacy-sensitive domains, such as healthcare and finance, is constrained by the scarcity of accessible training data due to stringent privacy requirements. Secure multi-party computation...

One-shot Face Sketch Synthesis in the Wild via Generative Diffusion Prior and Instruction Tuning

Face sketch synthesis is a technique aimed at converting face photos into sketches. Existing face sketch synthesis research mainly relies on training with numerous photo-sketch sample pairs from existing datasets. However, these large-scale discriminative learning methods will have to face proble...

CipherMind: the Longest Codebook in the World

In recent years, the widespread application of large language models has inspired us to consider using inference for communication encryption. We therefore propose CipherMind, which utilizes intermediate results from deterministic fine-tuning of large model inferences as transmission content. The...

CVE-2025-38083

In the Linux kernel, the following vulnerability has been resolved: netsched: prio: fix a race in priotune Gerrard Tai reported a race condition in PRIO, whenever SFQ perturb timer fires at the wrong time. The race is as follows: CPU 0 CPU 1 1: lock root 2: qdisctreeflushbacklog 3: unlock root | ...

Watermarking Autoregressive Image Generation

Watermarking the outputs of generative models has emerged as a promising approach for tracking their provenance. Despite significant interest in autoregressive image generation models and their potential for misuse, no prior work has attempted to watermark their outputs at the token level. In thi...

Differentiation-Based Extraction of Proprietary Data from Fine-Tuned LLMs

The increasing demand for domain-specific and human-aligned Large Language Models LLMs has led to the widespread adoption of Supervised Fine-Tuning SFT techniques. SFT datasets often comprise valuable instruction-response pairs, making them highly valuable targets for potential extraction. This...

PT-2025-37210

Name of the Vulnerable Software and Affected Versions: Linux kernel affected versions not specified Description: A buffer overflow issue was identified in the add tuning control function within the ALSA subsystem. The sprintf function call could exceed the allocated buffer size of 44 bytes if the...

Certified Unlearning for Neural Networks

We address the problem of machine unlearning, where the goal is to remove the influence of specific training data from a model upon request, motivated by privacy concerns and regulatory requirements such as the "right to be forgotten." Unfortunately, existing methods rely on restrictive assumptio...

IF-GUIDE: Influence Function-Guided Detoxification of LLMs

We study how training data contributes to the emergence of toxic behaviors in large-language models. Most prior work on reducing model toxicity adopts $reactive$ approaches, such as fine-tuning pre-trained and potentially toxic models to align them with human values. In contrast, we propose a...

Fedora 42 : bluez / iwd / libell (2025-35347bf9f0)

The remote Fedora 42 host has packages installed that are affected by multiple vulnerabilities as referenced in the FEDORA-2025-35347bf9f0 advisory. bluez 5.80: Fix issue with handling address type for all types of keys. Fix issue with handling maximum number of GATT channels. Fix issue with...

Why LLM Safety Guardrails Collapse after Fine-Tuning: a Similarity Analysis between Alignment and Fine-Tuning Datasets

Recent advancements in large language models LLMs have underscored their vulnerability to safety alignment jailbreaks, particularly when subjected to downstream fine-tuning. However, existing mitigation strategies primarily focus on reactively addressing jailbreak incidents after safety guardrail...

Learning to Diagnose Privately: DP-Powered LLMs for Radiology Report Classification

Purpose: This study proposes a framework for fine-tuning large language models LLMs with differential privacy DP to perform multi-abnormality classification on radiology report text. By injecting calibrated noise during fine-tuning, the framework seeks to mitigate the privacy risks associated wit...

Sylva: Tailoring Personalized Adversarial Defense in Pre-Trained Models Via Collaborative Fine-Tuning

Whitepaper called Sylva: Tailoring Personalized Adversarial Defense In Pre-Trained Models Via Collaborative Fine-Tuning...