Robustness Via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction

Large language models LLMs have demonstrated impressive performance and have come to dominate the field of natural language processing NLP across various tasks. However, due to their strong instruction-following capabilities and inability to distinguish between instructions and data content, LLMs...

GenPTW: In-Generation Image Watermarking for Provenance Tracing and Tamper Localization

The rapid development of generative image models has brought tremendous opportunities to AI-generated content AIGC creation, while also introducing critical challenges in ensuring content authenticity and copyright ownership. Existing image watermarking methods, though partially effective, often...

Prefill-Based Jailbreak: a Novel Approach of Bypassing LLM Safety Boundary

Large Language Models LLMs are designed to generate helpful and safe content. However, adversarial attacks, commonly referred to as jailbreak, can bypass their safety protocols, prompting LLMs to generate harmful content or reveal sensitive data. Consequently, investigating jailbreak methodologie...

AGATE: Stealthy Black-Box Watermarking for Multimodal Model Copyright Protection

Recent advancement in large-scale Artificial Intelligence AI models offering multimodal services have become foundational in AI systems, making them prime targets for model theft. Existing methods select Out-of-Distribution OoD data as backdoor watermarks and retrain the original model for...

Hybrid Privacy Policy-Code Consistency Check Using Knowledge Graphs and LLMs

The increasing concern in user privacy misuse has accelerated research into checking consistencies between smartphone apps' declared privacy policies and their actual behaviors. Recent advances in Large Language Models LLMs have introduced promising techniques for semantic comparison, but these...

PT-2025-17954 · Gl.Inet · Gl-A1300 Slate Plus +22

Name of the Vulnerable Software and Affected Versions: GL.iNet GL-A1300 Slate Plus version 4.x GL.iNet GL-AR300M16 Shadow version 4.x GL.iNet GL-AR300M Shadow version 4.x GL.iNet GL-AR750 Creta version 4.x GL.iNet GL-AR750S-EXT Slate version 4.x GL.iNet GL-AX1800 Flint version 4.x GL.iNet...

CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges

Large language models LLMs have demonstrated remarkable capabilities, especially the recent advancements in reasoning, such as o1 and o3, pushing the boundaries of AI. Despite these impressive achievements in mathematics and coding, the reasoning abilities of LLMs in domains requiring cryptograph...

Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control

Large language models LLMs have transformed the way we access information. These models are often tuned to refuse to comply with requests that are considered harmful and to produce responses that better align with the preferences of those who control the models. To understand how this "censorship...

Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMs

The challenge of ensuring Large Language Models LLMs align with societal standards is of increasing interest, as these models are still prone to adversarial jailbreaks that bypass their safety mechanisms. Identifying these vulnerabilities is crucial for enhancing the robustness of LLMs against su...

LLMpatronous: Harnessing the Power of LLMs for Vulnerability Detection

Despite the transformative impact of Artificial Intelligence AI across various sectors, cyber security continues to rely on traditional static and dynamic analysis tools, hampered by high false positive rates and superficial code comprehension. While generative AI offers promising automation...

Adversarial Attacks on LLM-As-A-Judge Systems: Insights from Prompt Injections

LLM as judge systems used to assess text quality code correctness and argument strength are vulnerable to prompt injection attacks. We introduce a framework that separates content author attacks from system prompt attacks and evaluate five models Gemma 3.27B Gemma 3.4B Llama 3.2 3B GPT 4 and Clau...

Revisiting Data Auditing in Large Vision-Language Models

With the surge of large language models LLMs, Large Vision-Language Models VLMs--which integrate vision encoders with LLMs for accurate visual grounding--have shown great potential in tasks like generalist agents and robotic control. However, VLMs are typically trained on massive web-scraped...

Avoiding Leakage Poisoning: Concept Interventions under Distribution Shifts

In this paper, we investigate how concept-based models CMs respond to out-of-distribution OOD inputs. CMs are interpretable neural architectures that first predict a set of high-level concepts e.g., stripes, black and then predict a task label from those concepts. In particular, we study the impa...

STCL: Curriculum Learning Strategies for Deep Learning Image Steganography Models

Whitepaper called STCL: Curriculum Learning Strategies For Deep Learning Image Steganography Models...

"Shifting Access Control Left" Using Asset and Goal Models

Access control needs have broad design implications, but access control specifications may be elicited before, during, or after these needs are captured. Because access control knowledge is distributed, we need to make knowledge asymmetries more transparent, and use expertise already available to...

CVE-2025-28025

TOTOLINK A830R V4.1.2cu.5182B20201102, A950RG V4.1.2cu.5161B20200903, A3000RU V5.9c.5185B20201128, and A3100R V4.1.2cu.5247B20211129 were found to contain a buffer overflow vulnerability in downloadFile.cgi through the v14 parameter...

Case Study: Fine-Tuning Small Language Models for Accurate and Private CWE Detection in Python Code

Large Language Models LLMs have demonstrated significant capabilities in understanding and analyzing code for security vulnerabilities, such as Common Weakness Enumerations CWEs. However, their reliance on cloud infrastructure and substantial computational requirements pose challenges for analyzi...

CVE-2025-28025

TOTOLINK A830R V4.1.2cu.5182B20201102, A950RG V4.1.2cu.5161B20200903, A3000RU V5.9c.5185B20201128, and A3100R V4.1.2cu.5247B20211129 were found to contain a buffer overflow vulnerability in downloadFile.cgi through the v14 parameter...

Automatically Generating Rules of Malicious Software Packages Via Large Language Model

Today's security tools predominantly rely on predefined rules crafted by experts, making them poorly adapted to the emergence of software supply chain attacks. To tackle this limitation, we propose a novel tool, RuleLLM, which leverages large language models LLMs to automate rule generation for O...

Private Federated Learning Using Preference-Optimized Synthetic Data

In practical settings, differentially private Federated learning DP-FL is the dominant method for training models from private, on-device client data. Recent work has suggested that DP-FL may be enhanced or outperformed by methods that use DP synthetic data Wu et al., 2024; Hou et al., 2024. The...