CVE-2025-31052

Deserialization of Untrusted Data vulnerability in themeton The Fashion - Model Agency One Page Beauty Theme nrgfashion allows Object Injection.This issue affects The Fashion - Model Agency One Page Beauty Theme: from n/a through = 1.4.4...

How to Build a Lean Security Model: 5 Lessons from River Island

In today’s security landscape, budgets are tight, attack surfaces are sprawling, and new threats emerge daily. Maintaining a strong security posture under these circumstances without a large team or budget can be a real challenge. Yet lean security models are not only possible - they can be highl...

LLMail-Inject: a Dataset from a Realistic Adaptive Prompt Injection Challenge

Indirect Prompt Injection attacks exploit the inherent limitation of Large Language Models LLMs to distinguish between instructions and data in their inputs. Despite numerous defense proposals, the systematic evaluation against adaptive adversaries remains limited, even when successful attacks ca...

LLMs Cannot Reliably Judge (Yet?): a Comprehensive Assessment on the Robustness of LLM-As-A-Judge

Large Language Models LLMs have demonstrated remarkable intelligence across various tasks, which has inspired the development and widespread adoption of LLM-as-a-Judge systems for automated model testing, such as red teaming and benchmarking. However, these systems are susceptible to adversarial...

Empirical Quantification of Spurious Correlations in Malware Detection

End-to-end deep learning exhibits unmatched performance for detecting malware, but such an achievement is reached by exploiting spurious correlations -- features with high relevance at inference time, but known to be useless through domain knowledge. While previous work highlighted that deep...

DiffUMI: Training-Free Universal Model Inversion Via Unconditional Diffusion for Face Recognition

Face recognition technology presents serious privacy risks due to its reliance on sensitive and immutable biometric data. To address these concerns, such systems typically convert raw facial images into embeddings, which are traditionally viewed as privacy-preserving. However, model inversion...

GenBreak: Red Teaming Text-To-Image Generators Using Large Language Models

Text-to-image T2I models such as Stable Diffusion have advanced rapidly and are now widely used in content creation. However, these models can be misused to generate harmful content, including nudity or violence, posing significant safety risks. While most platforms employ content moderation...

Learning Obfuscations of LLM Embedding Sequences: Stained Glass Transform

The high cost of ownership of AI compute infrastructure and challenges of robust serving of large language models LLMs has led to a surge in managed Model-as-a-service deployments. Even when enterprises choose on-premises deployments, the compute infrastructure is typically shared across many tea...

Expert-In-The-Loop Systems with Cross-Domain and In-Domain Few-Shot Learning for Software Vulnerability Detection

As cyber threats become more sophisticated, rapid and accurate vulnerability detection is essential for maintaining secure systems. This study explores the use of Large Language Models LLMs in software vulnerability assessment by simulating the identification of Python code with known Common...

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods

In this work, we show that some machine unlearning methods may fail when subjected to straightforward prompt attacks. We systematically evaluate eight unlearning techniques across three model families, and employ output-based, logit-based, and probe analysis to determine to what extent supposedly...

CVE-2025-47049

Adobe Experience Manager versions 6.5.22 and earlier are affected by a DOM-based Cross-Site Scripting XSS vulnerability. An attacker could exploit this issue by manipulating the DOM environment to execute malicious JavaScript within the context of the victim's browser. Exploitation of this issue...

Lean and Mean: How We Fine-Tuned a Small Language Model for Secret Detection in Code

Building an efficient small language model for cybersecurity, from data prep to deployment...

Securing Generative AI Agentic Workflows: Risks, Mitigation, and a Proposed Firewall Architecture

Generative Artificial Intelligence GenAI presents significant advancements but also introduces novel security challenges, particularly within agentic workflows where AI agents operate autonomously. These risks escalate in multi-agent systems due to increased interaction complexity. This paper...

DAVSP: Safety Alignment for Large Vision-Language Models Via Deep Aligned Visual Safety Prompt

Large Vision-Language Models LVLMs have achieved impressive progress across various applications but remain vulnerable to malicious queries that exploit the visual modality. Existing alignment approaches typically fail to resist malicious queries while preserving utility on benign ones effectivel...

Quantifying Mix Network Privacy Erosion with Generative Models

Modern mix networks improve over Tor and provide stronger privacy guarantees by robustly obfuscating metadata. As long as a message is routed through at least one honest mixnode, the privacy of the users involved is safeguarded. However, the complexity of the mixing mechanisms makes it difficult ...

TOTOLINK EX1200T 安全漏洞

The TOTOLINK EX1200T is a wireless router from TOTOLINK. A buffer overflow vulnerability exists in the TOTOLINK EX1200T version 4.1.2cu.5232B20210713, which affects the HTTP POST request processing component of file/boafrm/formFilter with unknown code. A remote attacker could exploit this...

The vulnerability of the AT+MMNAME command in the microprogramming software of Microhard IPn4Gii-NA2 and BulletLTE-NA2 allows a hacker to enhance their privileges.

The vulnerability of the AT+MMNAME command in the microprogramming software of Microhard IPn4Gii-NA2 and BulletLTE-NA2 lies in the implementation or modification of certain arguments. Exploiting this vulnerability can allow attackers to enhance their privileges...

Your Agent Can Defend Itself against Backdoor Attacks

Despite their growing adoption across domains, large language model LLM-powered agents face significant security risks from backdoor attacks during training and fine-tuning. These compromised agents can subsequently be manipulated to execute malicious operations when presented with specific...

Mono: Is Your "Clean" Vulnerability Dataset Really Solvable? Exposing and Trapping Undecidable Patches and Beyond

The quantity and quality of vulnerability datasets are essential for developing deep learning solutions to vulnerability-related tasks. Due to the limited availability of vulnerabilities, a common approach to building such datasets is analyzing security patches in source code. However, existing...

Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test

As API access becomes a primary interface to large language models LLMs, users often interact with black-box systems that offer little transparency into the deployed model. To reduce costs or maliciously alter model behaviors, API providers may discreetly serve quantized or fine-tuned variants,...