MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models

Model extraction attacks aim to replicate the functionality of a black-box model through query access, threatening the intellectual property IP of machine-learning-as-a-service MLaaS providers. Defending against such attacks is challenging, as it must balance efficiency, robustness, and utility...

Linksys多款产品 注入漏洞

Linksys RE6300 and others are products of Linksys, Inc.Linksys RE6300 is a wireless network signal extender.Linksys RE6250 is a wireless extender.Linksys RE6500 is a wireless extender. An injection vulnerability exists in various Linksys products, which stems from a command injection due to...

Linksys多款产品 安全漏洞

Linksys RE6300 and others are products of Linksys, Inc.Linksys RE6300 is a wireless network signal extender.Linksys RE6250 is a wireless extender.Linksys RE6500 is a wireless extender. A security vulnerability exists in various Linksys products, which stems from the incorrect operation of the...

Silence Is Golden: Leveraging Adversarial Examples to Nullify Audio Control in LDM-Based Talking-Head Generation

Advances in talking-head animation based on Latent Diffusion Models LDM enable the creation of highly realistic, synchronized videos. These fabricated videos are indistinguishable from real ones, increasing the risk of potential misuse for scams, political manipulation, and misinformation. Hence,...

Linksys多款产品 安全漏洞

Linksys RE6300 and others are products of Linksys, Inc.Linksys RE6300 is a wireless network signal extender.Linksys RE7000 is a wireless signal extender.Linksys RE6250 is a wireless extender. A security vulnerability exists in various Linksys products, which stems from the incorrect operation of...

Linksys多款产品 命令注入漏洞

Linksys RE6300 and others are products of Linksys, Inc.Linksys RE6300 is a wireless network signal extender.Linksys RE7000 is a wireless signal extender.Linksys RE6250 is a wireless extender. A command injection vulnerability exists in several Linksys products, which stems from the incorrect...

Linksys多款产品 安全漏洞

Linksys RE6300 and others are products of Linksys, Inc.Linksys RE6300 is a wireless network signal extender.Linksys RE6250 is a wireless extender.Linksys RE6500 is a wireless extender.Linksys RE6500 is a wireless extender.Linksys RE6500 is a wireless extender.Linksys RE6500 is a wireless...

Linksys多款产品 安全漏洞

Linksys RE6300 and others are products of Linksys, Inc.Linksys RE6300 is a wireless network signal extender.Linksys RE6250 is a wireless extender.Linksys RE6500 is a wireless extender. A security vulnerability exists in several Linksys products, which originates from an os command injection due t...

ReGA: Representation-Guided Abstraction for Model-Based Safeguarding of LLMs

Large Language Models LLMs have achieved significant success in various tasks, yet concerns about their safety and security have emerged. In particular, they pose risks in generating harmful content and vulnerability to jailbreaking attacks. To analyze and monitor machine learning models,...

A Systematic Review of Metaheuristics-Based and Machine Learning-Driven Intrusion Detection Systems in IoT

The widespread adoption of the Internet of Things IoT has raised a new challenge for developers since it is prone to known and unknown cyberattacks due to its heterogeneity, flexibility, and close connectivity. To defend against such security breaches, researchers have focused on building...

Autoregressive Images Watermarking through Lexical Biasing: an Approach Resistant to Regeneration Attack

Autoregressive AR image generation models have gained increasing attention for their breakthroughs in synthesis quality, highlighting the need for robust watermarking to prevent misuse. However, existing in-generation watermarking techniques are primarily designed for diffusion models, where...

PYSEC-2025-44

django-helpdesk before 1.0.0 allows Sensitive Data Exposure because of os.umask0 in models.py...

The Security Threat of Compressed Projectors in Large Vision-Language Models

The choice of a suitable visual language projector VLP is critical to the successful training of large visual language models LVLMs. Mainstream VLPs can be broadly categorized into compressed and uncompressed projectors, and each offering distinct advantages in performance and computational...

SafeGenes: Evaluating the Adversarial Robustness of Genomic Foundation Models

Genomic Foundation Models GFMs, such as Evolutionary Scale Modeling ESM, have demonstrated significant success in variant effect prediction. However, their adversarial robustness remains largely unexplored. To address this gap, we propose SafeGenes: a framework for Secure analysis of genomic...

Video Signature: In-Generation Watermarking for Latent Video Diffusion Models

The rapid development of Artificial Intelligence Generated Content AIGC has led to significant progress in video generation but also raises serious concerns about intellectual property protection and reliable content tracing. Watermarking is a widely adopted solution to this issue, but existing...

Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences

LLM generated code often contains security issues. We address two key challenges in improving secure code generation. First, obtaining high quality training data covering a broad set of security issues is critical. To address this, we introduce a method for distilling a preference dataset of...

Django-Helpdesk 安全漏洞

Django-Helpdesk is a Django application in the Django open source. It is used to manage internal helpdesk tickets. A security vulnerability exists in Django-Helpdesk versions prior to 1.0.0, which stems from os.umask0 in models.py leading to the exposure of sensitive data...

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models Via Non-Textual Modalities

Existing attacks against multimodal language models MLLMs primarily communicate instructions through text accompanied by adversarial images. In contrast, we exploit the capabilities of MLLMs to interpret non-textual instructions, specifically, adversarial images or audio generated by our novel...

CVE-2018-25111

CVE-2018-25111 affects django-helpdesk versions prior to 1.0.0. The root cause is os.umask(0) usage in models.py, which leads to exposure of sensitive data. Affected component: django-helpdesk (Python/Django app). Impact stated: sensitive data exposure with local access; no remote/external vector...

PYSEC-2025-54

vLLM is an inference and serving engine for large language models LLMs. In versions 0.8.0 up to but excluding 0.9.0, hitting the /v1/completions API with a invalid jsonschema as a Guided Param kills the vllm server. This vulnerability is similar GHSA-9hcf-v7m4-6m2j/CVE-2025-48943, but for regex...