Test-Time Immunization: a Universal Defense Framework against Jailbreaks for (Multimodal) Large Language Models

While multimodal large language models LLMs have attracted widespread attention due to their exceptional capabilities, they remain vulnerable to jailbreak attacks. Various defense methods are proposed to defend against jailbreak attacks, however, they are often tailored to specific types of...

Spa-VLM: Stealthy Poisoning Attacks on RAG-Based VLM

With the rapid development of the Vision-Language Model VLM, significant progress has been made in Visual Question Answering VQA tasks. However, existing VLM often generate inaccurate answers due to a lack of up-to-date knowledge. To address this issue, recent research has introduced...

GeneBreaker: Jailbreak Attacks against DNA Language Models with Pathogenicity Guidance

DNA, encoding genetic instructions for almost all living organisms, fuels groundbreaking advances in genomics and synthetic biology. Recently, DNA Foundation Models have achieved success in designing synthetic functional DNA sequences, even whole genomes, but their susceptibility to jailbreaking...

Permissioned LLMs: Enforcing Access Control in Large Language Models

In enterprise settings, organizational data is segregated, siloed and carefully protected by elaborate access control frameworks. These access control structures can completely break down if an LLM fine-tuned on the siloed data serves requests, for downstream tasks, from individuals with disparat...

Unveiling Impact of Frequency Components on Membership Inference Attacks for Diffusion Models

Diffusion models have achieved tremendous success in image generation, but they also raise significant concerns regarding privacy and copyright issues. Membership Inference Attacks MIAs are designed to ascertain whether specific data were utilized during a model's training phase. As current MIAs...

System Prompt Extraction Attacks and Defenses in Large Language Models

The system prompt in Large Language Models LLMs plays a pivotal role in guiding model behavior and response generation. Often containing private configuration details, user roles, and operational instructions, the system prompt has become an emerging attack target. Recent studies have shown that...

VideoMarkBench: Benchmarking Robustness of Video Watermarking

The rapid development of video generative models has led to a surge in highly realistic synthetic videos, raising ethical concerns related to disinformation and copyright infringement. Recently, video watermarking has been proposed as a mitigation strategy by embedding invisible marks into...

Weidmueller Interface多款产品 安全漏洞

Weidmueller Interface E-SW-VL08MT-8TX and others are products of Weidmueller Interface, Germany.Weidmueller Interface E-SW-VL08MT-8TX is a managed network switch.Weidmueller Interface IE-SW-PL10M-3GT-7TX is an Ethernet switch.Weidmueller Interface IE-SW-PL10MT-3GT-7TX is a managed network switch....

Malicious code in ideals-models (npm)

The package communicates with a domain associated with malicious activity. --- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 9094b69aeede7f54491271e3aa85e2daed3a13e32c5bea91b73721225061b2d1 Any computer that has this package installed or running should be considered...

MAL-2025-4480 Malicious code in ideals-models (npm)

The package communicates with a domain associated with malicious activity. --- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 9094b69aeede7f54491271e3aa85e2daed3a13e32c5bea91b73721225061b2d1 Any computer that has this package installed or running should be considered...

Semantic-Preserving Adversarial Attacks on LLMs: an Adaptive Greedy Binary Search Approach

Large Language Models LLMs increasingly rely on automatic prompt engineering in graphical user interfaces GUIs to refine user inputs and enhance response accuracy. However, the diversity of user requirements often leads to unintended misinterpretations, where automated optimizations distort...

One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP

Deep Neural Networks DNNs have achieved widespread success yet remain prone to adversarial attacks. Typically, such attacks either involve frequent queries to the target model or rely on surrogate models closely mirroring the target model -- often trained with subsets of the target model's traini...

PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks

Large language models LLMs have achieved remarkable capabilities but remain vulnerable to adversarial prompts known as jailbreaks, which can bypass safety alignment and elicit harmful outputs. Despite growing efforts in LLM safety research, existing evaluations are often fragmented, focused on...

Phare: a Safety Probe for Large Language Models

Ensuring the safety of large language models LLMs is critical for responsible deployment, yet existing evaluations often prioritize performance over identifying failure modes. We introduce Phare, a multilingual diagnostic framework to probe and evaluate LLM behavior across three critical...

CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models

Retrieval-Augmented Generation RAG enhances large language models LLMs by incorporating external knowledge, but its openness introduces vulnerabilities that can be exploited by poisoning attacks. Existing poisoning methods for RAG systems have limitations, such as poor generalization and lack of...

Capability-Based Scaling Laws for LLM Red-Teaming

As large language models grow in capability and agency, identifying vulnerabilities through red-teaming becomes vital for safe deployment. However, traditional prompt-engineering approaches may prove ineffective once red-teaming turns into a weak-to-strong problem, where target models surpass...

Zero-Trust Foundation Models: a New Paradigm for Secure and Collaborative Artificial Intelligence for Internet of Things

This paper focuses on Zero-Trust Foundation Models ZTFMs, a novel paradigm that embeds zero-trust security principles into the lifecycle of foundation models FMs for Internet of Things IoT systems. By integrating core tenets, such as continuous verification, least privilege access LPA, data...

MixBridge: Heterogeneous Image-To-Image Backdoor Attack through Mixture of Schrödinger Bridges

This paper focuses on implanting multiple heterogeneous backdoor triggers in bridge-based diffusion models designed for complex and arbitrary input distributions. Existing backdoor formulations mainly address single-attack scenarios and are limited to Gaussian noise input models. To fill this gap...

CoTGuard: Using Chain-Of-Thought Triggering for Copyright Protection in Multi-Agent LLM Systems

As large language models LLMs evolve into autonomous agents capable of collaborative reasoning and task execution, multi-agent LLM systems have emerged as a powerful paradigm for solving complex problems. However, these systems pose new challenges for copyright protection, particularly when...

Netcore多款产品 注入漏洞

Netcore NBR1005GPEV2 and so on are products of China Leike Netcore.Netcore NBR1005GPEV2 is a full gigabit multi-WAN port POE-powered enterprise AP management multifunctional wired router.Netcore B6V2 is a full gigabit wireless router.Netcore COVER5 is an enterprise-class router. An injection...