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...

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...

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 ...

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...

Scaling Patterns in Adversarial Alignment: Evidence from Multi-LLM Jailbreak Experiments

Large language models LLMs increasingly operate in multi-agent and safety-critical settings, raising open questions about how their vulnerabilities scale when models interact adversarially. This study examines whether larger models can systematically jailbreak smaller ones - eliciting harmful or...

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...

GRAPHTEXTACK: A Realistic Black-Box Node Injection Attack on LLM-Enhanced GNNs

Text-attributed graphs TAGs, which combine structural and textual node information, are ubiquitous across many domains. Recent work integrates Large Language Models LLMs with Graph Neural Networks GNNs to jointly model semantics and structure, resulting in more general and expressive models that...

Data Poisoning Vulnerabilities across Healthcare AI Architectures: A Security Threat Analysis

Healthcare AI systems face major vulnerabilities to data poisoning that current defenses and regulations cannot adequately address. We analyzed eight attack scenarios in four categories: architectural attacks on convolutional neural networks, large language models, and reinforcement learning...

Adaptive Intrusion Detection for Evolving RPL IoT Attacks Using Incremental Learning

The routing protocol for low-power and lossy networks RPL has become the de facto routing standard for resource-constrained IoT systems, but its lightweight design exposes critical vulnerabilities to a wide range of routing-layer attacks such as hello flood, decreased rank, and version number...

HP Integrated Lights-Out Improper Neutralization of Input During Web Page Generation (CVE-2021-29206)

"A remote xss vulnerability was discovered in HPE Integrated Lights-Out 4 iLO 4 %NASLMINLEVEL 80900 C Tenable, Inc. include'compat.inc'; if description scriptid504401; scriptversion"1.1"; scriptsetattributeattribute:"pluginmodificationdate", value:"2025/11/13"; scriptcveid"CVE-2021-29206";...

How Worrying Are Privacy Attacks against Machine Learning?

In several jurisdictions, the regulatory framework on the release and sharing of personal data is being extended to machine learning ML. The implicit assumption is that disclosing a trained ML model entails a privacy risk for any personal data used in training comparable to directly releasing tho...

MTAttack: Multi-Target Backdoor Attacks against Large Vision-Language Models

Recent advances in Large Visual Language Models LVLMs have demonstrated impressive performance across various vision-language tasks by leveraging large-scale image-text pretraining and instruction tuning. However, the security vulnerabilities of LVLMs have become increasingly concerning,...

Can AI Models Be Jailbroken to Phish Elderly Victims? an End-To-End Evaluation

We present an end-to-end demonstration of how attackers can exploit AI safety failures to harm vulnerable populations: from jailbreaking LLMs to generate phishing content, to deploying those messages against real targets, to successfully compromising elderly victims. We systematically evaluated...

Phantom Menace: Exploring and Enhancing the Robustness of VLA Models against Physical Sensor Attacks

Vision-Language-Action VLA models revolutionize robotic systems by enabling end-to-end perception-to-action pipelines that integrate multiple sensory modalities, such as visual signals processed by cameras and auditory signals captured by microphones. This multi-modality integration allows VLA...

How Can We Effectively Use LLMs for Phishing Detection?: Evaluating the Effectiveness of Large Language Model-Based Phishing Detection Models

Large language models LLMs have emerged as a promising phishing detection mechanism, addressing the limitations of traditional deep learning-based detectors, including poor generalization to previously unseen websites and a lack of interpretability. However, LLMs' effectiveness for phishing...