Fully segregated networks? Your dual-homed devices might disagree

TL;DR Using dual-homed devices as a segregation tool is not recommended as a security design solution Use dedicated hardware and robust firewalls to segregate networks to limit access to critical networks Proactively check for unintended exposure of network services and disable unnecessary servic...

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models Via Objective-Decoupled Optimization

Vision-Language-Action VLA models have advanced robotic control by enabling end-to-end decision-making directly from multimodal inputs. However, their tightly coupled architectures expose novel security vulnerabilities. Unlike traditional adversarial perturbations, backdoor attacks represent a...

GSDFuse: Capturing Cognitive Inconsistencies from Multi-Dimensional Weak Signals in Social Media Steganalysis

The ubiquity of social media platforms facilitates malicious linguistic steganography, posing significant security risks. Steganalysis is profoundly hindered by the challenge of identifying subtle cognitive inconsistencies arising from textual fragmentation and complex dialogue structures, and th...

Training-Free Watermarking for Autoregressive Image Generation

Invisible image watermarking can protect image ownership and prevent malicious misuse of visual generative models. However, existing generative watermarking methods are mainly designed for diffusion models while watermarking for autoregressive image generation models remains largely underexplored...

Agency Problems and Adversarial Bilevel Optimization under Uncertainty and Cyber Threats

We study an agency problem between a holding company and its subsidiary, exposed to cyber threats that affect the overall value of the subsidiary. The holding company seeks to design an optimal incentive scheme to mitigate these losses. In response, the subsidiary selects an optimal cybersecurity...

Is Artificial Intelligence Generated Image Detection a Solved Problem?

The rapid advancement of generative models, such as GANs and Diffusion models, has enabled the creation of highly realistic synthetic images, raising serious concerns about misinformation, deepfakes, and copyright infringement. Although numerous Artificial Intelligence Generated Image AIGI...

Self-Destructive Language Model

Harmful fine-tuning attacks pose a major threat to the security of large language models LLMs, allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment, they fail to address models' inherent "trainability" on harmfu...

Coded Robust Aggregation for Distributed Learning under Byzantine Attacks

In this paper, we investigate the problem of distributed learning DL in the presence of Byzantine attacks. For this problem, various robust bounded aggregation RBA rules have been proposed at the central server to mitigate the impact of Byzantine attacks. However, current DL methods apply RBA rul...

Adversarially Robust Spiking Neural Networks with Sparse Connectivity

Deployment of deep neural networks in resource-constrained embedded systems requires innovative algorithmic solutions to facilitate their energy and memory efficiency. To further ensure the reliability of these systems against malicious actors, recent works have extensively studied adversarial...

Robust Federated Learning with Confidence-Weighted Filtering and GAN-Based Completion under Noisy and Incomplete Data

Federated learning FL presents an effective solution for collaborative model training while maintaining data privacy across decentralized client datasets. However, data quality issues such as noisy labels, missing classes, and imbalanced distributions significantly challenge its effectiveness. Th...

OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models

Large language models LLMs trained over extensive corpora risk memorizing sensitive, copyrighted, or toxic content. To address this, we propose OBLIVIATE, a robust unlearning framework that removes targeted data while preserving model utility. The framework follows a structured process: extractin...

PT-2025-18727 · Webmin · Webmin

Name of the Vulnerable Software and Affected Versions: Webmin versions prior to 2.302 Description: A critical vulnerability in Webmin allows authenticated remote attackers to escalate privileges to root-level, risking severe server compromise. The vulnerability is caused by improper CRLF sequence...

TriniMark: a Robust Generative Speech Watermarking Method for Trinity-Level Attribution

Whitepaper called TriniMark: A Robust Generative Speech Watermarking Method For Trinity-Level Attribution...

Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMs

The challenge of ensuring Large Language Models LLMs align with societal standards is of increasing interest, as these models are still prone to adversarial jailbreaks that bypass their safety mechanisms. Identifying these vulnerabilities is crucial for enhancing the robustness of LLMs against su...

Enhancing Variational Autoencoders with Smooth Robust Latent Encoding

Variational Autoencoders VAEs have played a key role in scaling up diffusion-based generative models, as in Stable Diffusion, yet questions regarding their robustness remain largely underexplored. Although adversarial training has been an established technique for enhancing robustness in predicti...

FLARE: Feature-Based Lightweight Aggregation for Robust Evaluation of IoT Intrusion Detection

The proliferation of Internet of Things IoT devices has expanded the attack surface, necessitating efficient intrusion detection systems IDSs for network protection. This paper presents FLARE, a feature-based lightweight aggregation for robust evaluation of IoT intrusion detection to address the...

SOLIDO: a Robust Watermarking Method for Speech Synthesis Via Low-Rank Adaptation

Whitepaper called SOLIDO: A Robust Watermarking Method For Speech Synthesis Via Low-Rank Adaptation...

How to Enhance Downstream Adversarial Robustness (Almost) without Touching the Pre-Trained Foundation Model?

With the rise of powerful foundation models, a pre-training-fine-tuning paradigm becomes increasingly popular these days: A foundation model is pre-trained using a huge amount of data from various sources, and then the downstream users only need to fine-tune and adapt it to specific downstream...

Concept Enhancement Engineering: a Lightweight and Efficient Robust Defense against Jailbreak Attacks in Embodied AI

Embodied Intelligence EI systems integrated with large language models LLMs face significant security risks, particularly from jailbreak attacks that manipulate models into generating harmful outputs or executing unsafe physical actions. Traditional defense strategies, such as input filtering and...

[SECURITY] Fedora 42 Update: tree-sitter-0.25.2-8.fc42

Tree-sitter is a parser generator tool and an incremental parsing library. It can build a concrete syntax tree for a source file and efficiently update the syntax tree as the source file is edited. Tree-sitter aims to be: General enough to parse any programming language Fast enough to parse on...