Extending the OWASP Multi-Agentic System Threat Modeling Guide: Insights from Multi-Agent Security Research

We propose an extension to the OWASP Multi-Agentic System MAS Threat Modeling Guide, translating recent anticipatory research in multi-agent security MASEC into practical guidance for addressing challenges unique to large language model LLM-driven multi-agent architectures. Although OWASP's...

Secure Authentication Via Quantum Physical Unclonable Functions: a Review

Quantum Physical Unclonable Functions QPUFs offer a physically grounded approach to secure authentication, extending the capabilities of classical PUFs. This review covers their theoretical foundations and key implementation challenges - such as quantum memories and Haar-randomness -, and...

Exploring Cross-Stage Adversarial Transferability in Class-Incremental Continual Learning

Class-incremental continual learning addresses catastrophic forgetting by enabling classification models to preserve knowledge of previously learned classes while acquiring new ones. However, the vulnerability of the models against adversarial attacks during this process has not been investigated...

Linux Distros Unpatched Vulnerability : CVE-2025-38122

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - In the Linux kernel, the following vulnerability has been resolved: gve: add missing NULL check for gveallocpendingpacket in TX DQO gveallocpendingpacket can...

ProvX: Generating Counterfactual-Driven Attack Explanations for Provenance-Based Detection

Provenance graph-based intrusion detection systems are deployed on hosts to defend against increasingly severe Advanced Persistent Threat. Using Graph Neural Networks to detect these threats has become a research focus and has demonstrated exceptional performance. However, the widespread adoption...

Prompt Injection Vulnerability of Consensus Generating Applications in Digital Democracy

Large Language Models LLMs are gaining traction as a method to generate consensus statements and aggregate preferences in digital democracy experiments. Yet, LLMs may introduce critical vulnerabilities in these systems. Here, we explore the impact of prompt-injection attacks targeting consensus...

A Survey on Data Security in Large Language Models

Large Language Models LLMs, now a foundation in advancing natural language processing, power applications such as text generation, machine translation, and conversational systems. Despite their transformative potential, these models inherently rely on massive amounts of training data, often...

NCCR: to Evaluate the Robustness of Neural Networks and Adversarial Examples

Neural networks have received a lot of attention recently, and related security issues have come with it. Many studies have shown that neural networks are vulnerable to adversarial examples that have been artificially perturbed with modification, which is too small to be distinguishable by human...

The vulnerability of the rgxfw_write_robustness_buffer() function in the Driver Development Kit (DDK) toolset allows a hacker to gain unauthorized access to protected information.

The vulnerability of the rgxfwwriterobustnessbuffer function in the Driver Development Kit DDK toolset is related to context privilege switching errors. Exploiting this vulnerability can allow an attacker to gain unauthorized access to protected information...

Secure One-Sided Device-Independent Quantum Key Distribution under Collective Attacks with Enhanced Robustness

We study the security of a quantum key distribution QKD protocol under the one-sided device-independent 1sDI setting, which assumes trust in only one party's measurement device. This approach effectively provides a balance between the experimental viability of device-dependent DD-QKD and the...

Unmasking Synthetic Realities in Generative AI: a Comprehensive Review of Adversarially Robust Deepfake Detection Systems

The rapid advancement of Generative Artificial Intelligence has fueled deepfake proliferation-synthetic media encompassing fully generated content and subtly edited authentic material-posing challenges to digital security, misinformation mitigation, and identity preservation. This systematic revi...

Enhancing Resilience against Jamming Attacks: a Cooperative Anti-Jamming Method Using Direction Estimation

The inherent vulnerability of wireless communication necessitates strategies to enhance its security, particularly in the face of jamming attacks. This paper uses the collaborations of multiple sensing nodes SNs in the wireless network to present a cooperative anti-jamming approach CAJ designed t...

REAL-IoT: Characterizing GNN Intrusion Detection Robustness under Practical Adversarial Attack

Graph Neural Network GNN-based network intrusion detection systems NIDS are often evaluated on single datasets, limiting their ability to generalize under distribution drift. Furthermore, their adversarial robustness is typically assessed using synthetic perturbations that lack realism. This...

LaSM: Layer-Wise Scaling Mechanism for Defending Pop-Up Attack on GUI Agents

Graphical user interface GUI agents built on multimodal large language models MLLMs have recently demonstrated strong decision-making abilities in screen-based interaction tasks. However, they remain highly vulnerable to pop-up-based environmental injection attacks, where malicious visual element...

Phishing Detection in the Gen-AI Era: Quantized LLMs Vs Classical Models

Phishing attacks are becoming increasingly sophisticated, underscoring the need for detection systems that strike a balance between high accuracy and computational efficiency. This paper presents a comparative evaluation of traditional Machine Learning ML, Deep Learning DL, and quantized...

RAG Safety: Exploring Knowledge Poisoning Attacks to Retrieval-Augmented Generation

Retrieval-Augmented Generation RAG enhances large language models LLMs by retrieving external data to mitigate hallucinations and outdated knowledge issues. Benefiting from the strong ability in facilitating diverse data sources and supporting faithful reasoning, knowledge graphs KGs have been...

Evaluating the Evaluators: Trust in Adversarial Robustness Tests

Despite significant progress in designing powerful adversarial evasion attacks for robustness verification, the evaluation of these methods often remains inconsistent and unreliable. Many assessments rely on mismatched models, unverified implementations, and uneven computational budgets, which ca...

When There Is No Decoder: Removing Watermarks from Stable Diffusion Models in a No-Box Setting

Watermarking has emerged as a promising solution to counter harmful or deceptive AI-generated content by embedding hidden identifiers that trace content origins. However, the robustness of current watermarking techniques is still largely unexplored, raising critical questions about their...

CVE-2025-38124

CVE-2025-38124 pertains to the Linux kernel UDP/GSO path. The vulnerability arises when UDP GSO fragments within a frag_list are not correctly linearized after a pull from frag_list, causing invalid geometry for skb_segment. The fix, as described in commit a1e40ac5b5e9, redirects and then lineari...

CVE-2025-38122

In CVE-2025-38122, the Linux kernel vulnerability is due to a missing NULL check in gve_alloc_pending_packet() used by gve_tx_add_skb_dqo(). The function can return NULL, but the caller did not guard against this, risking NULL pointer dereference in low‑memory scenarios. The fix adds the missing ...