Steering in the Shadows: Causal Amplification for Activation Space Attacks in Large Language Models

Modern large language models LLMs are typically secured by auditing data, prompts, and refusal policies, while treating the forward pass as an implementation detail. We show that intermediate activations in decoder-only LLMs form a vulnerable attack surface for behavioral control. Building on...

Multi-Faceted Attack: Exposing Cross-Model Vulnerabilities in Defense-Equipped Vision-Language Models

The growing misuse of Vision-Language Models VLMs has led providers to deploy multiple safeguards, including alignment tuning, system prompts, and content moderation. However, the real-world robustness of these defenses against adversarial attacks remains underexplored. We introduce Multi-Faceted...

"To Survive, I Must Defect": Jailbreaking LLMs Via the Game-Theory Scenarios

As LLMs become more common, non-expert users can pose risks, prompting extensive research into jailbreak attacks. However, most existing black-box jailbreak attacks rely on hand-crafted heuristics or narrow search spaces, which limit scalability. Compared with prior attacks, we propose Game-Theor...

Password Strength Analysis through Social Network Data Exposure: A Combined Approach Relying on Data Reconstruction and Generative Models

Although passwords remain the primary defense against unauthorized access, users often tend to use passwords that are easy to remember. This behavior significantly increases security risks, also due to the fact that traditional password strength evaluation methods are often inadequate. In this...

PT-2025-47649

Name of the Vulnerable Software and Affected Versions vLLM versions 0.5.5 through 0.11.0 Description vLLM is an inference and serving engine for large language models LLMs. Users can cause the vLLM engine to crash when serving multimodal models by providing multimodal embedding inputs with a...

CVE-2025-63209

The ELCA Star Transmitter Remote Control firmware 1.25 for STAR150, BP1000, STAR300, STAR2000, STAR1000, STAR500, and possibly other models, contains an information disclosure vulnerability allowing unauthenticated attackers to retrieve admin credentials and system settings via an unprotected...

CVE-2025-13305

A weakness has been identified in D-Link DWR-M920, DWR-M921, DWR-M960, DIR-822K and DIR-825M 1.01.07. This issue affects some unknown processing of the file /boafrm/formTracerouteDiagnosticRun. Executing manipulation of the argument host can lead to buffer overflow. The attack may be launched...

Small Language Models for Phishing Website Detection: Cost, Performance, and Privacy Trade-Offs

Phishing websites pose a major cybersecurity threat, exploiting unsuspecting users and causing significant financial and organisational harm. Traditional machine learning approaches for phishing detection often require extensive feature engineering, continuous retraining, and costly infrastructur...

Trustworthy GenAI over 6G: Integrated Applications and Security Frameworks

The integration of generative artificial intelligence GenAI into 6G networks promises substantial performance gains while simultaneously exposing novel security vulnerabilities rooted in multimodal data processing and autonomous reasoning. This article presents a unified perspective on cross-doma...

Can MLLMs Detect Phishing? A Comprehensive Security Benchmark Suite Focusing on Dynamic Threats and Multimodal Evaluation in Academic Environments

The rapid proliferation of Multimodal Large Language Models MLLMs has introduced unprecedented security challenges, particularly in phishing detection within academic environments. Academic institutions and researchers are high-value targets, facing dynamic, multilingual, and context-dependent...

VulnCheck KEV: CVE-2024-12912

An improper input insertion vulnerability in AiCloud on certain router models may lead to arbitrary command execution. Refer to the '01/02/2025 ASUS Router AiCloud vulnerability' section on the ASUS Security Advisory for more information...

CVE-2025-13304

A security flaw has been discovered in D-Link DWR-M920, DWR-M921, DWR-M960, DWR-M961 and DIR-825M 1.01.07/1.1.47. This vulnerability affects unknown code of the file /boafrm/formPingDiagnosticRun. Performing manipulation of the argument host results in buffer overflow. The attack may be initiated...

CVE-2025-13305 D-Link DWR-M920/DWR-M921/DWR-M960/DIR-822K/DIR-825M formTracerouteDiagnosticRun buffer overflow

A weakness has been identified in D-Link DWR-M920, DWR-M921, DWR-M960, DIR-822K and DIR-825M 1.01.07. This issue affects some unknown processing of the file /boafrm/formTracerouteDiagnosticRun. Executing manipulation of the argument host can lead to buffer overflow. The attack may be launched...

CVE-2025-13304

CVE-2025-13304 affects multiple D-Link routers: DWR-M920, DWR-M921, DWR-M960, DWR-M961, and DIR-825M (firmware 1.01.07/1.1.47). The flaw lies in the file path /boafrm/formPingDiagnosticRun; adversarial manipulation of the “host” argument can cause a buffer overflow, enabling a remote attack. Docu...

Collaborative research by Microsoft and NVIDIA on real-time immunity

AI-Powered Threats Demand AI-Powered Defense While AI supports growth and innovation, it is also reshaping how organizations address faster, more adaptive security risks. AI-driven security threats, including “vibe-hacking”, are evolving faster than traditional defenses can adapt. Attackers can n...

EchoGram Flaw Bypasses Guardrails in Major LLMs

HiddenLayer reveals the EchoGram vulnerability, which bypasses safety guardrails on GPT-5.1 and other major LLMs, giving security teams just a 3-month head start...

VEIL: Jailbreaking Text-To-Video Models Via Visual Exploitation from Implicit Language

Jailbreak attacks can circumvent model safety guardrails and reveal critical blind spots. Prior attacks on text-to-video T2V models typically add adversarial perturbations to obviously unsafe prompts, which are often easy to detect and defend. In contrast, we show that benign-looking prompts...

DualTAP: A Dual-Task Adversarial Protector for Mobile MLLM Agents

The reliance of mobile GUI agents on Multimodal Large Language Models MLLMs introduces a severe privacy vulnerability: screenshots containing Personally Identifiable Information PII are often sent to untrusted, third-party routers. These routers can exploit their own MLLMs to mine this data,...

Jailbreaking Large Vision Language Models in Intelligent Transportation Systems

Large Vision Language Models LVLMs demonstrate strong capabilities in multimodal reasoning and many real-world applications, such as visual question answering. However, LVLMs are highly vulnerable to jailbreaking attacks. This paper systematically analyzes the vulnerabilities of LVLMs integrated ...

Whose Narrative Is It Anyway? A KV Cache Manipulation Attack

The Key ValueKV cache is an important component for efficient inference in autoregressive Large Language Models LLMs, but its role as a representation of the model's internal state makes it a potential target for integrity attacks. This paper introduces "History Swapping," a novel block-level...