MAL-2025-32936 Malicious code in semantic-ui-restart-solarnebula-borealis (npm)

The package semantic-ui-restart-solarnebula-borealis was found to contain malicious code...

MAL-2025-22123 Malicious code in hadron-planetology-izar-semantic-release (npm)

The package hadron-planetology-izar-semantic-release was found to contain malicious code...

MAL-2025-18727 Malicious code in draco-lacerta-process-semantic-ui (npm)

The package draco-lacerta-process-semantic-ui was found to contain malicious code...

Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-Cache in LLM Inference

The Key-Value KV cache, which stores intermediate attention computations Key and Value pairs to avoid redundant calculations, is a fundamental mechanism for accelerating Large Language Model LLM inference. However, this efficiency optimization introduces significant yet underexplored privacy risk...

Attacks and Defenses against LLM Fingerprinting

As large language models are increasingly deployed in sensitive environments, fingerprinting attacks pose significant privacy and security risks. We present a study of LLM fingerprinting from both offensive and defensive perspectives. Our attack methodology uses reinforcement learning to...

Mitigating Distribution Shift in Graph-Based Android Malware Classification Via Function Metadata and LLM Embeddings

Graph-based malware classifiers can achieve over 94% accuracy on standard Android datasets, yet we find they suffer accuracy drops of up to 45% when evaluated on previously unseen malware variants from the same family - a scenario where strong generalization would typically be expected. This...

Semantic Encryption: Secure and Effective Interaction with Cloud-Based Large Language Models Via Semantic Transformation

The increasing adoption of Cloud-based Large Language Models CLLMs has raised significant concerns regarding data privacy during user interactions. While existing approaches primarily focus on encrypting sensitive information, they often overlook the logical structure of user inputs. This oversig...

Empirical Evaluation of Concept Drift in ML-Based Android Malware Detection

Despite outstanding results, machine learning-based Android malware detection models struggle with concept drift, where rapidly evolving malware characteristics degrade model effectiveness. This study examines the impact of concept drift on Android malware detection, evaluating two datasets and...

ConSeg: Contextual Backdoor Attack against Semantic Segmentation

Despite significant advancements in computer vision, semantic segmentation models may be susceptible to backdoor attacks. These attacks, involving hidden triggers, aim to cause the models to misclassify instances of the victim class as the target class when triggers are present, posing serious...

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...

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...

Accelerating Automatic Program Repair with Dual Retrieval-Augmented Fine-Tuning and Patch Generation on Large Language Models

Automated Program Repair APR is essential for ensuring software reliability and quality while enhancing efficiency and reducing developers' workload. Although rule-based and learning-based APR methods have demonstrated their effectiveness, their performance was constrained by the defect type of...

3S-Attack: Spatial, Spectral and Semantic Invisible Backdoor Attack against DNN Models

Backdoor attacks involve either poisoning the training data or directly modifying the model in order to implant a hidden behavior, that causes the model to misclassify inputs when a specific trigger is present. During inference, the model maintains high accuracy on benign samples but misclassifie...

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...

CLIProv: a Contrastive Log-To-Intelligence Multimodal Approach for Threat Detection and Provenance Analysis

With the increasing complexity of cyberattacks, the proactive and forward-looking nature of threat intelligence has become more crucial for threat detection and provenance analysis. However, translating high-level attack patterns described in Tactics, Techniques, and Procedures TTP intelligence...

Shuffling for Semantic Secrecy

Deep learning draws heavily on the latest progress in semantic communications. The present paper aims to examine the security aspect of this cutting-edge technique from a novel shuffling perspective. Our goal is to improve upon the conventional secure coding scheme to strike a desirable tradeoff...

LIFT: Automating Symbolic Execution Optimization with Large Language Models for AI Networks

Dynamic Symbolic Execution DSE is a key technique in program analysis, widely used in software testing, vulnerability discovery, and formal verification. In distributed AI systems, DSE plays a crucial role in identifying hard-to-detect bugs, especially those arising from complex network...

Enhancing Phishing Detection in Financial Systems through NLP

The threat of phishing attacks in financial systems is continuously growing. Therefore, protecting sensitive information from unauthorized access is paramount. This paper discusses the critical need for robust email phishing detection. Several existing methods, including blacklists and whitelists...

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...

SAMEP: a Secure Protocol for Persistent Context Sharing across AI Agents

Current AI agent architectures suffer from ephemeral memory limitations, preventing effective collaboration and knowledge sharing across sessions and agent boundaries. We introduce SAMEP Secure Agent Memory Exchange Protocol, a novel framework that enables persistent, secure, and semantically...