JsDeObsBench: Measuring and Benchmarking LLMs for JavaScript Deobfuscation

Deobfuscating JavaScript JS code poses a significant challenge in web security, particularly as obfuscation techniques are frequently used to conceal malicious activities within scripts. While Large Language Models LLMs have recently shown promise in automating the deobfuscation process,...

ZKPROV: a Zero-Knowledge Approach to Dataset Provenance for Large Language Models

As the deployment of large language models LLMs grows in sensitive domains, ensuring the integrity of their computational provenance becomes a critical challenge, particularly in regulated sectors such as healthcare, where strict requirements are applied in dataset usage. We introduce ZKPROV, a...

Diffusion-Based Task-Oriented Semantic Communications with Model Inversion Attack

Semantic communication has emerged as a promising neural network-based system design for 6G networks. Task-oriented semantic communication is a novel paradigm whose core goal is to efficiently complete specific tasks by transmitting semantic information, optimizing communication efficiency and ta...

Assessing Risk of Stealing Proprietary Models for Medical Imaging Tasks

The success of deep learning in medical imaging applications has led several companies to deploy proprietary models in diagnostic workflows, offering monetized services. Even though model weights are hidden to protect the intellectual property of the service provider, these models are exposed to...

llama.cpp 安全漏洞

llama.cpp is a multimodal model by the individual developer Georgi Gerganov. A security vulnerability exists in versions of llama.cpp prior to b5721, which stems from the presence of signed and unsigned integer overflows in the tokenizer implementation, which could lead to a heap overflow...

FuncVul: an Effective Function Level Vulnerability Detection Model Using LLM and Code Chunk

Software supply chain vulnerabilities arise when attackers exploit weaknesses by injecting vulnerable code into widely used packages or libraries within software repositories. While most existing approaches focus on identifying vulnerable packages or libraries, they often overlook the specific...

Hitachi Relion 安全漏洞

Hitachi Relion is used by Hitachi, Ltd. of Japan to protect, control, measure, and monitor for power systems. A security vulnerability exists in Hitachi Relion that stems from improper disk space management and may cause the device to reboot. The following models are affected: 670, 650 and...

Recalling the Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacy

Machine Unlearning MU technology facilitates the removal of the influence of specific data instances from trained models on request. Despite rapid advancements in MU technology, its vulnerabilities are still under explored, posing potential risks of privacy breaches through leaks of ostensibly...

Decompiling Smart Contracts with a Large Language Model

The widespread lack of broad source code verification on blockchain explorers such as Etherscan, where despite 78,047,845 smart contracts deployed on Ethereum as of May 26, 2025, a mere 767,520 1% are open source, presents a severe impediment to blockchain security. This opacity necessitates the...

RepuNet: a Reputation System for Mitigating Malicious Clients in DFL

Decentralized Federated Learning DFL enables nodes to collaboratively train models without a central server, introducing new vulnerabilities since each node independently selects peers for model aggregation. Malicious nodes may exploit this autonomy by sending corrupted models model poisoning,...

CLSA-2025-1750688636 gcc: Fix of CVE-2020-11023

CVE-2020-11023: sanitize HTML content passed to DOM manipulation methods to prevent execution of untrusted code...

Google Adds Multi-Layered Defenses to Secure GenAI from Prompt Injection Attacks

Google has revealed the various safety measures that are being incorporated into its generative artificial intelligence AI systems to mitigate emerging attack vectors like indirect prompt injections and improve the overall security posture for agentic AI systems. "Unlike direct prompt injections,...

SparkKitty, SparkCat’s little brother: A new Trojan spy found in the App Store and Google Play

Update 25.06.2025: Apple removed the malicious app from the App Store. In January 2025, we uncovered the SparkCat spyware campaign, which was aimed at gaining access to victims' crypto wallets. The threat actor distributed apps containing a malicious SDK/framework. This component would wait for a...

Enhancing Security in LLM Applications: a Performance Evaluation of Early Detection Systems

Prompt injection threatens novel applications that emerge from adapting LLMs for various user tasks. The newly developed LLM-based software applications become more ubiquitous and diverse. However, the threat of prompt injection attacks undermines the security of these systems as the mitigation a...

Towards Provable (In)Secure Model Weight Release Schemes

Recent secure weight release schemes claim to enable open-source model distribution while protecting model ownership and preventing misuse. However, these approaches lack rigorous security foundations and provide only informal security guarantees. Inspired by established works in cryptography, we...

Private Model Personalization Revisited

Whitepaper called Private Model Personalization Revisited...

Deep CNN Face Matchers Inherently Support Revocable Biometric Templates

One common critique of biometric authentication is that if an individual's biometric is compromised, then the individual has no recourse. The concept of revocable biometrics was developed to address this concern. A biometric scheme is revocable if an individual can have their current enrollment i...

The vulnerability of the SIGLENT SDS1000X-E oscilloscope is related to deficiencies in access control, allowing an intruder to execute arbitrary commands and trigger a service failure.

The vulnerability of the SIGLENT SDS1000X-E oscilloscope is related to deficiencies in access control. Exploiting this vulnerability could allow an intruder to execute arbitrary commands and cause service failures...

Restoring Gaussian Blurred Face Images for Deanonymization Attacks

Gaussian blur is widely used to blur human faces in sensitive photos before the photos are posted on the Internet. However, it is unclear to what extent the blurred faces can be restored and used to re-identify the person, especially under a high-blurring setting. In this paper, we explore this...

FAME: a Lightweight Spatio-Temporal Network for Model Attribution of Face-Swap Deepfakes

The widespread emergence of face-swap Deepfake videos poses growing risks to digital security, privacy, and media integrity, necessitating effective forensic tools for identifying the source of such manipulations. Although most prior research has focused primarily on binary Deepfake detection, th...