Invisible Injections: Exploiting Vision-Language Models through Steganographic Prompt Embedding

Vision-language models VLMs have revolutionized multimodal AI applications but introduce novel security vulnerabilities that remain largely unexplored. We present the first comprehensive study of steganographic prompt injection attacks against VLMs, where malicious instructions are invisibly...

Secure Goal-Oriented Communication: Defending against Eavesdropping Timing Attacks

Goal-oriented Communication GoC is a new paradigm that plans data transmission to occur only when it is instrumental for the receiver to achieve a certain goal. This leads to the advantage of reducing the frequency of transmissions significantly while maintaining adherence to the receiver's...

Reporte De Vulnerabilidades En IIoT. Proyecto DEFENDER

The main objective of this technical report is to conduct a comprehensive study on devices operating within Industrial Internet of Things IIoT environments, describing the scenarios that define this category and analysing the vulnerabilities that compromise their security. To this end, the report...

A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures

In recent years, Large-Language-Model-driven AI agents have exhibited unprecedented intelligence, flexibility, and adaptability, and are rapidly changing human production and lifestyle. Nowadays, agents are undergoing a new round of evolution. They no longer act as an isolated island like LLMs...

SoK: Advances and Open Problems in Web Tracking

Web tracking is a pervasive and opaque practice that enables personalized advertising, retargeting, and conversion tracking. Over time, it has evolved into a sophisticated and invasive ecosystem, employing increasingly complex techniques to monitor and profile users across the web. The research...

A Large Language Model-Supported Threat Modeling Framework for Transportation Cyber-Physical Systems

Modern transportation systems rely on cyber-physical systems CPS, where cyber systems interact seamlessly with physical systems like transportation-related sensors and actuators to enhance safety, mobility, and energy efficiency. However, growing automation and connectivity increase exposure to...

IOLeak - CPU Side Channel Attacks

AMD ID: AMD-SB-7042 Potential Impact: N/A Severity: N/A Summary Researchers have provided AMD with a summary of relevant remarks and findings detailed in a paper titled “IOLeak Side-Channel Attack Exploiting CPU Frequency Scaling and I/O Latency.” AMD reviewed the summary and believes this attack...

Siemens SIRIUS

SUMMARY SIRIUS 3SK2 Safety Relays and 3RK3 Modular Safety Systems only provide weak password obfuscation. An attacker with access to the PROFINET or serial interface of the device could eavesdrop or read the stored password from the device and de-obfuscate it. The safety passwords work as...

Siemens Desigo

SUMMARY Desigo CC deployments that use Installed Client are impacted by an information disclosure vulnerability which could result in information leak from the Desigo CC server. The other Desigo CC client options, Windows App Client and Flex Client, are not affected by this vulnerability...

ssh: Prefix truncation attack on Binary Packet Protocol (BPP)

A flaw was found in the SSH channel integrity. By manipulating sequence numbers during the handshake, an attacker can remove the initial messages on the secure channel without causing a MAC failure. For example, an attacker could disable the ping extension and thus disable the new countermeasure ...

A Comprehensive Study of Exploitable Patterns in Smart Contracts: from Vulnerability to Defense

With the rapid advancement of blockchain technology, smart contracts have enabled the implementation of increasingly complex functionalities. However, ensuring the security of smart contracts remains a persistent challenge across the stages of development, compilation, and execution...

CVE-2025-3301

DPA countermeasures are unavailable for ECDH key agreement and EdDSA signing operations on Curve25519 and Curve448 on all Series 2 modules and SoCs due to a lack of hardware and software support. A successful DPA attack may result in exposure of confidential information. The best practice is to u...

CVE-2025-3301 DPA Countermeasures Unavailable for Certain Cryptographic Operations on Series 2 Devices

DPA countermeasures are unavailable for ECDH key agreement and EdDSA signing operations on Curve25519 and Curve448 on all Series 2 modules and SoCs due to a lack of hardware and software support. A successful DPA attack may result in exposure of confidential information. The best practice is to u...

CVE-2025-3301

CVE-2025-3301 concerns DPA countermeasures being unavailable for ECDH key agreement and EdDSA signing on Curve25519 and Curve448 on all Series 2 modules and SoCs due to lack of hardware and software support. The consequence is potential exposure of confidential information if a DPA attack is succ...

CVE-2025-3301 DPA Countermeasures Unavailable for Certain Cryptographic Operations on Series 2 Devices

DPA countermeasures are unavailable for ECDH key agreement and EdDSA signing operations on Curve25519 and Curve448 on all Series 2 modules and SoCs due to a lack of hardware and software support. A successful DPA attack may result in exposure of confidential information. The best practice is to u...

PT-2025-18163 · Series 2 · Series 2

Name of the Vulnerable Software and Affected Versions: Series 2 modules and SoCs affected versions not specified Description: A lack of hardware and software support for DPA countermeasures in ECDH key agreement and EdDSA signing operations on Curve25519 and Curve448 may result in exposure of...

SoK: Security of EMV Contactless Payment Systems

The widespread adoption of EMV Europay, Mastercard, and Visa contactless payment systems has greatly improved convenience for both users and merchants. However, this growth has also exposed significant security challenges. This SoK provides a comprehensive analysis of security vulnerabilities in...

Network-Centric Countermeasures against Integrated Sensing Enabled Jamming Adversaries

Recent developments in Integrated Sensing and Communication have led to new adversarial models in wireless security through Integrated Sensing and Jamming ISAJ adversaries. ISAJ adversaries, owing to their sensing capabilities, are known to inject jamming energy over the victim's frequency band,...

On the Feasibility of Using MultiModal LLMs to Execute AR Social Engineering Attacks

Augmented Reality AR and Multimodal Large Language Models LLMs are rapidly evolving, providing unprecedented capabilities for human-computer interaction. However, their integration introduces a new attack surface for social engineering. In this paper, we systematically investigate the feasibility...

ARCeR: an Agentic RAG for the Automated Definition of Cyber Ranges

The growing and evolving landscape of cybersecurity threats necessitates the development of supporting tools and platforms that allow for the creation of realistic IT environments operating within virtual, controlled settings as Cyber Ranges CRs. CRs can be exploited for analyzing vulnerabilities...