Protecting On-Device AI Inference: A Systematic Review of Attacks and Defence Mechanisms

The need for secure and private Artificial Intelligence AI and Machine Learning ML on edge and mobile devices has increased the necessity of protecting the architecture of these systems from threats to both security and privacy. With an ever-increasing number of pre-trained AI models being used o...

Autonomous LLM Agent Worms: Cross-Platform Propagation, Automated Discovery and Temporal Re-Entry Defense

Autonomous LLM agents operate as long-running processes with persistent workspaces, memory files, scheduled task state, and messaging integrations. These features create a new propagation risk: attacker-influenced content can be written into persistent agent state, re-enter the LLM decision conte...

The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey

AI agents that combine large language models with non-AI system components are rapidly emerging in real-world applications, offering unprecedented automation and flexibility. However, this unprecedented flexibility introduces complex security challenges fundamentally different from those in...

Security in the Era of Perceptive Networks: A Comprehensive Taxonomic Framework for Integrated Sensing and Communication Security

Integrated Sensing and Communication ISAC represents a significant shift in the 6G landscape, where wireless networks both sense the environment and communicate. While prior comprehensive surveys have established foundational elements of ISAC security, discussed perception-focused security models...

An Empirical Study on the Security Vulnerabilities of GPTs

Equipped with various tools and knowledge, GPTs, one kind of customized AI agents based on OpenAI's large language models, have illustrated great potential in many fields, such as writing, research, and programming. Today, the number of GPTs has reached three millions, with the range of specific...

Beyond a Single Perspective: Towards a Realistic Evaluation of Website Fingerprinting Attacks

Website Fingerprinting WF attacks exploit patterns in encrypted traffic to infer the websites visited by users, posing a serious threat to anonymous communication systems. Although recent WF techniques achieve over 90% accuracy in controlled experimental settings, most studies remain confined to...

A Comprehensive Survey of Website Fingerprinting Attacks and Defenses in Tor: Advances and Open Challenges

The Tor network provides users with strong anonymity by routing their internet traffic through multiple relays. While Tor encrypts traffic and hides IP addresses, it remains vulnerable to traffic analysis attacks such as the website fingerprinting WF attack, achieving increasingly high...

EUVD-2019-3431

Malware in sbrugna...

EUVD-2019-7560

Malware in sbrugna...

Exploit Tool Invocation Prompt for Tool Behavior Hijacking in LLM-Based Agentic System

LLM-based agentic systems leverage large language models to handle user queries, make decisions, and execute external tools for complex tasks across domains like chatbots, customer service, and software engineering. A critical component of these systems is the Tool Invocation Prompt TIP, which...

Smart Car Privacy: Survey of Attacks and Privacy Issues

Automobiles are becoming increasingly important in our day to day life. Modern automobiles are highly computerized and hence potentially vulnerable to attack. Providing many wireless connectivity for vehicles enables a bridge between vehicles and their external environments. Such a connected...

Exploring Traffic Simulation and Cybersecurity Strategies Using Large Language Models

Intelligent Transportation Systems ITS are increasingly vulnerable to sophisticated cyberattacks due to their complex, interconnected nature. Ensuring the cybersecurity of these systems is paramount to maintaining road safety and minimizing traffic disruptions. This study presents a novel...

BESA: Boosting Encoder Stealing Attack with Perturbation Recovery

To boost the encoder stealing attack under the perturbation-based defense that hinders the attack performance, we propose a boosting encoder stealing attack with perturbation recovery named BESA. It aims to overcome perturbation-based defenses. The core of BESA consists of two modules: perturbati...

PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks

Large language models LLMs have achieved remarkable capabilities but remain vulnerable to adversarial prompts known as jailbreaks, which can bypass safety alignment and elicit harmful outputs. Despite growing efforts in LLM safety research, existing evaluations are often fragmented, focused on...

One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems

Large Language Models LLMs enhanced with Retrieval-Augmented Generation RAG have shown improved performance in generating accurate responses. However, the dependence on external knowledge bases introduces potential security vulnerabilities, particularly when these knowledge bases are publicly...

Security-First AI: Foundations for Robust and Trustworthy Systems

The conversation around artificial intelligence AI often focuses on safety, transparency, accountability, alignment, and responsibility. However, AI security i.e., the safeguarding of data, models, and pipelines from adversarial manipulation underpins all of these efforts. This manuscript posits...

Token-Level Constraint Boundary Search for Jailbreaking Text-To-Image Models

Recent advancements in Text-to-Image T2I generation have significantly enhanced the realism and creativity of generated images. However, such powerful generative capabilities pose risks related to the production of inappropriate or harmful content. Existing defense mechanisms, including prompt...

Preventing Bot Attacks and Online Fraud on APIs

The rapid proliferation of Application Programming Interfaces APIs is spearheading digital transformation, leading to explosive growth in adoption of APIs in recent years. In fact, it’s hard to think of any software that doesn’t use or is in itself, an API. By supporting swift development and...

CVE-2019-11761

By using a form with a data URI it was possible to gain access to the privileged JSONView object that had been cloned into content. Impact from exposing this object appears to be minimal, however it was a bypass of existing defense in depth mechanisms. This vulnerability affects Firefox 70,...

Manipulating Machine Learning Systems by Manipulating Training Data

Interesting research: "TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agents": Abstract:: Recent work has identified that classification models implemented as neural networks are vulnerable to data-poisoning and Trojan attacks at training time. In this work, we show that these training-ti...