DecipherGuard: Understanding and Deciphering Jailbreak Prompts for a Safer Deployment of Intelligent Software Systems

Intelligent software systems powered by Large Language Models LLMs are increasingly deployed in critical sectors, raising concerns about their safety during runtime. Through an industry-academic collaboration when deploying an LLM-powered virtual customer assistant, a critical software engineerin...

WordPress Rank Math SEO plugin <= 1.0.252.1 - Sensitive Data Exposure vulnerability

Sensitive Data Exposure vulnerability discovered by Abu Hurayra in WordPress Plugin Rank Math SEO versions = 1.0.252.1...

WordPress Rank Math SEO plugin <= 1.0.252.1 - Broken Access Control vulnerability

Broken Access Control vulnerability discovered by Abu Hurayra in WordPress Plugin Rank Math SEO versions = 1.0.252.1...

Cryptographic Application of Elliptic Curve with High Rank

Elliptic curve cryptography is better than traditional cryptography based on RSA and discrete logarithm of finite field in terms of efficiency and security. In this paper, we show how to exploit elliptic curve with high rank, which has not been used in cryptography before, to construct...

MPOCryptoML: Multi-Pattern Based Off-Chain Crypto Money Laundering Detection

Recent advancements in money laundering detection have demonstrated the potential of using graph neural networks to capture laundering patterns accurately. However, existing models are not explicitly designed to detect the diverse patterns of off-chain cryptocurrency money laundering. Neglecting...

Machine Learning-Based AES Key Recovery Via Side-Channel Analysis on the ASCAD Dataset

Cryptographic algorithms like AES and RSA are widely used and they are mathematically robust and almost unbreakable but its implementation on physical devices often leak information through side channels, such as electromagnetic EM emissions, potentially compromising said theoretically secure...

BERTector: Intrusion Detection Based on Joint-Dataset Learning

Intrusion detection systems IDS are facing challenges in generalization and robustness due to the heterogeneity of network traffic and the diversity of attack patterns. To address this issue, we propose a new joint-dataset training paradigm for IDS and propose a scalable BERTector framework based...

A Comparative Analysis of Lightweight Hash Functions Using AVR ATXMega128 and ChipWhisperer

Lightweight hash functions have become important building blocks for security in embedded and IoT systems. A plethora of algorithms have been proposed and standardized, providing a wide range of performance trade-off options for developers to choose from. This paper presents a comparative analysi...

Hot-Swap MarkBoard: an Efficient Black-Box Watermarking Approach for Large-Scale Model Distribution

Recently, Deep Learning DL models have been increasingly deployed on end-user devices as On-Device AI, offering improved efficiency and privacy. However, this deployment trend poses more serious Intellectual Property IP risks, as models are distributed on numerous local devices, making them...

HumanSAM: Classifying Human-Centric Forgery Videos in Human Spatial, Appearance, and Motion Anomaly

Numerous synthesized videos from generative models, especially human-centric ones that simulate realistic human actions, pose significant threats to human information security and authenticity. While progress has been made in binary forgery video detection, the lack of fine-grained understanding ...

LoRA-Leak: Membership Inference Attacks against LoRA Fine-Tuned Language Models

Language Models LMs typically adhere to a "pre-training and fine-tuning" paradigm, where a universal pre-trained model can be fine-tuned to cater to various specialized domains. Low-Rank Adaptation LoRA has gained the most widespread use in LM fine-tuning due to its lightweight computational cost...

CVE-2025-7579 chinese-poetry server.js redos

A vulnerability was found in chinese-poetry 0.1. It has been rated as problematic. This issue affects some unknown processing of the file rank/server.js. The manipulation leads to inefficient regular expression complexity. The attack may be initiated remotely. The exploit has been disclosed to th...

Differentially Private Federated Low Rank Adaptation beyond Fixed-Matrix

Large language models LLMs typically require fine-tuning for domain-specific tasks, and LoRA offers a computationally efficient approach by training low-rank adapters. LoRA is also communication-efficient for federated LLMs when multiple users collaboratively fine-tune a global LLM model without...

CVE-2025-7579: Inefficient Regular Expression Complexity

A vulnerability was found in chinese-poetry 0.1. It has been rated as problematic. This issue affects some unknown processing of the file rank/server.js. The manipulation leads to inefficient regular expression complexity. The attack may be initiated remotely. The exploit has been disclosed to th...

chinese-poetry 安全漏洞

chinese-poetry is chinese-poetry open source a database of ancient Chinese poems. A security vulnerability exists in chinese-poetry version 0.1, which stems from an insufficient regular expression complexity due to a misbehavior in the file rank/server.js...

LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA Sharing

The proliferation of Low-Rank Adaptation LoRA models has democratized personalized text-to-image generation, enabling users to share lightweight models e.g., personal portraits on platforms like Civitai and Liblib. However, this "share-and-play" ecosystem introduces critical risks: benign LoRAs c...

Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA

Memorization in large language models LLMs makes them vulnerable to data extraction attacks. While pre-training memorization has been extensively studied, fewer works have explored its impact in fine-tuning, particularly for LoRA fine-tuning, a widely adopted parameter-efficient method. In this...

Navigating the Deep: Signature Extraction on Deep Neural Networks

Neural network model extraction has emerged in recent years as an important security concern, as adversaries attempt to recover a network's parameters via black-box queries. A key step in this process is signature extraction, which aims to recover the absolute values of the network's weights laye...

Sudoku: Decomposing DRAM Address Mapping into Component Functions

Decomposing DRAM address mappings into component-level functions is critical for understanding memory behavior and enabling precise RowHammer attacks, yet existing reverse-engineering methods fall short. We introduce novel timing-based techniques leveraging DRAM refresh intervals and consecutive...

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,...