conftrace_

black-box attack

237 papers

Explore in graph

Co-occurring keywords

adversarial attack (1621) adversarial example (564) query efficiency (70) adversarial perturbation (384) neural network (6616) adversarial transferability (46) deep neural network (1803) model robustness (480) white-box attack (38) decision-based attack (12)

Papers

When Background Matters: Breaking Medical Vision Language Models by Transferable Attack ACL 2026

Adversarial Attack on Black-Box Multi-Agent by Adaptive Perturbation AAAI 2026

HogVul: Black-box Adversarial Code Generation Framework Against LM-based Vulnerability Detectors AAAI 2026

CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems ACL 2026

Fading the Digital Ink: A Universal Black-Box Attack Framework for 3DGS Watermarking Systems AAAI 2026

Transferability of Adversarial Attacks in Video-based MLLMs: A Cross-modal Image-to-Video Approach AAAI 2026

Token-Level Precise Attack on RAG: Searching for the Best Alternatives to Mislead Generation EACL 2026

Privacy Leaks by Adversaries: Adversarial Iterations for Membership Inference Attack AAAI 2026

Manipulating the Mind’s Eye: A-SAGE, the Attention-Based Attack on ViT Explainability AAAI 2026

CoLA: A Choice Leakage Attack Framework to Expose Privacy Risks in Subset Training ACL 2026

Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization ACL 2026

Black-Box Membership Inference Attacks for Video Training Data in Multimodal Large Language Models ACL 2026

AD2: Analysis and Detection of Adversarial Threats in Visual Perception for End-to-End Autonomous Driving Systems WACV 2026

LAMP: Learning Universal Adversarial Perturbations for Multi-Image Tasks via Pre-trained Models AAAI 2026

Zer0-Jack: A memory-efficient gradient-based jailbreaking method for black box Multi-modal Large Language Models EACL 2026

VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy EACL 2026

Prompting Adversarial Transferability via Path Flatness Attack AAAI 2026

JailPO: A Novel Black-Box Jailbreak Framework via Preference Optimization Against Aligned LLMs AAAI 2025

Towards a 3D Transfer-based Black-box Attack via Critical Feature Guidance ICCV 2025

KOEnsAttack: Towards Efficient Data-Free Black-Box Adversarial Attacks via Knowledge-Orthogonalized Substitute Ensembles ICCV 2025

Power of Diversity: Enhancing Data-Free Black-Box Attack with Domain-Augmented Learning AAAI 2025

ADBA: Approximation Decision Boundary Approach for Black-Box Adversarial Attacks AAAI 2025

Reinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion Filters AAAI 2025

Enhancing Adversarial Transferability with Adversarial Weight Tuning AAAI 2025

Mind the Gap: Detecting Black-box Adversarial Attacks in the Making through Query Update Analysis CVPR 2025