CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage

Model compression is crucial for minimizing memory storage and accelerating inference in deep learning DL models, including recent foundation models like large language models LLMs. Users can access different compressed model versions according to their resources and budget. However, while existi...

Talking like a Phisher: LLM-Based Attacks on Voice Phishing Classifiers

Voice phishing vishing remains a persistent threat in cybersecurity, exploiting human trust through persuasive speech. While machine learning ML-based classifiers have shown promise in detecting malicious call transcripts, they remain vulnerable to adversarial manipulations that preserve semantic...

GATEBLEED: Exploiting On-Core Accelerator Power Gating for High Performance and Stealthy Attacks on AI

As power consumption from AI training and inference continues to increase, AI accelerators are being integrated directly into the CPU. Intel's Advanced Matrix Extensions AMX is one such example, debuting on the 4th generation Intel Xeon Scalable CPU. We discover a timing side and covert channel,...

LLMxCPG: Context-Aware Vulnerability Detection through Code Property Graph-Guided Large Language Models

Software vulnerabilities present a persistent security challenge, with over 25,000 new vulnerabilities reported in the Common Vulnerabilities and Exposures CVE database in 2024 alone. While deep learning based approaches show promise for vulnerability detection, recent studies reveal critical...

How Search Engines, LLMs, and Third-Party Scrapers Affect Bot Management

...

SynthCTI: LLM-Driven Synthetic CTI Generation to Enhance MITRE Technique Mapping

Cyber Threat Intelligence CTI mining involves extracting structured insights from unstructured threat data, enabling organizations to understand and respond to evolving adversarial behavior. A key task in CTI mining is mapping threat descriptions to MITRE ATT&CK techniques. However, this process...

In-Context Learning of Vision Language Models for Detection of Physical and Digital Attacks against Face Recognition Systems

Recent advances in biometric systems have significantly improved the detection and prevention of fraudulent activities. However, as detection methods improve, attack techniques become increasingly sophisticated. Attacks on face recognition systems can be broadly divided into physical and digital...

Exploiting Context-Dependent Duration Features for Voice Anonymization Attack Systems

The temporal dynamics of speech, encompassing variations in rhythm, intonation, and speaking rate, contain important and unique information about speaker identity. This paper proposes a new method for representing speaker characteristics by extracting context-dependent duration embeddings from...

Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques

Large Language Models LLMs are transforming cybersecurity by enabling intelligent, adaptive, and automated approaches to threat detection, vulnerability assessment, and incident response. With their advanced language understanding and contextual reasoning, LLMs surpass traditional methods in...

Space Cybersecurity Testbed: Fidelity Framework, Example Implementation, and Characterization

Cyber threats against space infrastructures, including satellites and systems on the ground, have not been adequately understood. Testbeds are important to deepen our understanding and validate space cybersecurity studies. The state of the art is that there are very few studies on building...

ZWX-2000CSW2-HN and ZWX-2000CS2-HN vulnerable to use of hard-coded credentials

Overview ZWX-2000CSW2-HN and ZWX-2000CS2-HN provided by ZEXELON CO., LTD. contain the following vulnerability. Use of Hard-coded Credentials CWE-798 - CVE-2025-53842 This vulnerability is caused by an insufficient fix for CVE-2024-39838 JVN70666401. Hiroki Sato of Institute of Science Tokyo...

Introducing Akamai Cloud Pulse: Observability for Your Cloud Infrastructure – Now in Open Beta

...

From VPN to Zero Trust: Why It’s Time to Retire Traditional VPNs, Part 2

...

DOGE Denizen Marko Elez Leaked API Key for xAI

Marko Elez , a 25-year-old employee at Elon Musk's Department of Government Efficiency DOGE, has been granted access to sensitive databases at the U.S. Social Security Administration, the Treasury and Justice departments, and the Department of Homeland Security. So it should fill all Americans wi...

Mitigating Trojanized Prompt Chains in Educational LLM Use Cases: Experimental Findings and Detection Tool Design

The integration of Large Language Models LLMs in K--12 education offers both transformative opportunities and emerging risks. This study explores how students may Trojanize prompts to elicit unsafe or unintended outputs from LLMs, bypassing established content moderation systems with safety...

Multi-Trigger Poisoning Amplifies Backdoor Vulnerabilities in LLMs

Recent studies have shown that Large Language Models LLMs are vulnerable to data poisoning attacks, where malicious training examples embed hidden behaviours triggered by specific input patterns. However, most existing works assume a phrase and focus on the attack's effectiveness, offering limite...

WaFusion: a Wavelet-Enhanced Diffusion Framework for Face Morph Generation

Biometric face morphing poses a critical challenge to identity verification systems, undermining their security and robustness. To address this issue, we propose WaFusion, a novel framework combining wavelet decomposition and diffusion models to generate high-quality, realistic morphed face image...

From .pth to p0wned: Abuse of Pickle Files in AI Model Supply Chains

Executive summary Recent threat research highlights a growing risk in the Python and machine learning ML ecosystem: the exploitation of serialized model files, specifically those using Python’s pickle module. While commonly used for saving and loading ML models, pickle files can execute arbitrary...

The Man behind the Sound: Demystifying Audio Private Attribute Profiling Via Multimodal Large Language Model Agents

Our research uncovers a novel privacy risk associated with multimodal large language models MLLMs: the ability to infer sensitive personal attributes from audio data -- a technique we term audio private attribute profiling. This capability poses a significant threat, as audio can be covertly...

From Semantic Web and MAS to Agentic AI: a Unified Narrative of the Web of Agents

The concept of the Web of Agents WoA, which transforms the static, document-centric Web into an environment of autonomous agents acting on users' behalf, has attracted growing interest as large language models LLMs become more capable. However, research in this area is still fragmented across...