Learning-to-Detect

Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models Official implementation of “Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models.” This repository contains the data-processing, hidden-state extraction, classifier training, safety-pattern...

Selective Channel Restoration for Backdoored Vision-Language Models

Vision-language models VLMs exhibit strong multimodal capabilities but remain vulnerable to backdoors implanted through poisoned fine-tuning data. Existing defenses often require extensive parameter updates during fine-tuning or incur per-query overhead during inference. To address these...

Repeat-After-Me: Black-Box Adaptive Visual Prompt Injection

Prompt injection is widely recognized as a major security threat to AI agents that interact with untrusted external data, such as websites, documents, and emails. Prior work has shown that, in the text domain, black-box prompt injection can achieve near-perfect attack success rates ASRs. In the...

Decoy Images Amplify Caption-Mediated Defenses against Encoded Jailbreaks

We report a counter-intuitive interaction between image inputs and existing black-box defenses on Vision--Language Models VLMs: pairing an encoded jailbreak prompt with an unrelated decoy image can sharply lower attack success rate ASR. The operative change is in the defense pipeline, not in the...

(A)I Sees What You Don't: Exploiting New Attack Surfaces in Third-Party Mobile Agents

Third-party mobile agents powered by Vision-Language Models VLMs have emerged as a promising paradigm for automating smartphone interactions. These agents act as high-privilege decision-makers, perceiving device states through screenshots and executing actions via VLM reasoning, transforming how ...

MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents Via User-Generated Content

Mobile graphical user interface GUI agents driven by vision-language models VLMs perceive the screen as rendered pixels and choose actions from what they see, so they cannot reliably separate trusted interface elements from user-generated content. We present MIRAGE Mobile Injection of Realistic...

STARE: Step-Wise Temporal Alignment and Red-Teaming Engine for Multi-Modal Toxicity Attack

Red-teaming Vision-Language Models is essential for identifying vulnerabilities where adversarial image-text inputs trigger toxic outputs. Existing approaches treat image generation as a black box, returning only terminal toxicity scores and leaving open the question of when and how toxic semanti...

Hidden Ads: Behavior Triggered Semantic Backdoors for Advertisement Injection in Vision Language Models

Vision-Language Models VLMs are increasingly deployed in consumer applications where users seek recommendations about products, dining, and services. We introduce Hidden Ads, a new class of backdoor attacks that exploit this recommendation-seeking behavior to inject unauthorized advertisements...

Shape and Substance: Dual-Layer Side-Channel Attacks on Local Vision-Language Models

On-device Vision-Language Models VLMs promise data privacy via local execution. However, we show that the architectural shift toward Dynamic High-Resolution preprocessing e.g., AnyRes introduces an inherent algorithmic side-channel. Unlike static models, dynamic preprocessing decomposes images in...

TreeTeaming: Autonomous Red-Teaming of Vision-Language Models Via Hierarchical Strategy Exploration

The rapid advancement of Vision-Language Models VLMs has brought their safety vulnerabilities into sharp focus. However, existing red teaming methods are fundamentally constrained by an inherent linear exploration paradigm, confining them to optimizing within a predefined strategy set and...

VisualLeakBench: Auditing the Fragility of Large Vision-Language Models against PII Leakage and Social Engineering

As Large Vision-Language Models LVLMs are increasingly deployed in agent-integrated workflows and other deployment-relevant settings, their robustness against semantic visual attacks remains under-evaluated -- alignment is typically tested on explicit harmful content rather than privacy-critical...

Jailbreaking LLMs and VLMs: Mechanisms, Evaluation, and Unified Defense

This paper provides a systematic survey of jailbreak attacks and defenses on Large Language Models LLMs and Vision-Language Models VLMs, emphasizing that jailbreak vulnerabilities stem from structural factors such as incomplete training data, linguistic ambiguity, and generative uncertainty. It...

UIXPOSE: Mobile Malware Detection Via Intention-Behaviour Discrepancy Analysis

We introduce UIXPOSE, a source-code-agnostic framework that operates on both compiled and open-source apps. This framework applies Intention Behaviour Alignment IBA to mobile malware analysis, aligning UI-inferred intent with runtime semantics. Previous work either infers intent statically, e.g.,...

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...

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 ...

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,...

Evaluation of Vision-LLMs in Surveillance Video

The widespread use of cameras in our society has created an overwhelming amount of video data, far exceeding the capacity for human monitoring. This presents a critical challenge for public safety and security, as the timely detection of anomalous or criminal events is crucial for effective...

MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-Of-Experts LLMs

The transformer architecture has become a cornerstone of modern AI, fueling remarkable progress across applications in natural language processing, computer vision, and multimodal learning. As these models continue to scale explosively for performance, implementation efficiency remains a critical...

Enhancing Targeted Adversarial Attacks on Large Vision-Language Models through Intermediate Projector Guidance

Targeted adversarial attacks are essential for proactively identifying security flaws in Vision-Language Models before real-world deployment. However, current methods perturb images to maximize global similarity with the target text or reference image at the encoder level, collapsing rich visual...

Proactive Disentangled Modeling of Trigger-Object Pairings for Backdoor Defense

Deep neural networks DNNs and generative AI GenAI are increasingly vulnerable to backdoor attacks, where adversaries embed triggers into inputs to cause models to misclassify or misinterpret target labels. Beyond traditional single-trigger scenarios, attackers may inject multiple triggers across...