paper-with-me

Adversarial Attack

3개 벤치마크 · 논문 1,998편 · 이 태스크의 논문 보기 →

Benchmarks

CIFAR-10

결과 8개

CIFAR-100

결과 2개

WSJ0-2mix

결과 1개

Most implemented

Papers

Large-scale Testing Global Optimization Methods with Black-box Adversarial Attacks

2026-08-13 · Wojciech Zarzecki, Jarosław Arabas arxiv

Existing global optimization benchmark suites are of a moderate size and are based on a small number of analytical functions that date back even to the 1970s. This causes a risk of biasing the development of global optim…

Adversarial Attack

Universal Concept Disruption for SAM3 Image Segmentation

2026-08-06 · Hao Wang, Yuxuan Zhang, Wei Yang arxiv

SAM3 extends promptable segmentation from geometry-driven mask prediction to open-vocabulary concept segmentation, where a text-conditioned grounding model decides whether a concept is present and segments all matching i…

Adversarial RobustnessImage SegmentationAdversarial Attack

MissClick: Exploiting Digit-Serialized Coordinates to Attack GUI Grounding Models

2026-08-04 · Yu Ran, Wentao Zhao, Xin Zhang, Yi Pan arxiv

Recent GUI visual grounding models generate screen coordinates as sequences of digit tokens that are parsed into numerical values and mapped to executable clicks. The security implications of this coordinate generation p…

Adversarial AttackVisual Grounding

Adversarial Deepfake Generation and an Investigation of Purification-Based Adversarial Detection

2026-07-28 · Junghyun Kim, Seunghyun Kim, Jiyoung Woo arxiv

This paper describes the participation of team "Go To Germany" in the ImageCLEF 2026 Deepfake Detection and Generation Task. For the image generation task, we employ FLUX.1-dev with PuLID for identity-preserving face syn…

DeepFake DetectionAdversarial AttackImage Generation

GeoThreat: Transferable Targeted Adversarial Attacks on Large Vision-Language Models for Remote Sensing Image Interpretation

2026-07-23 · Yimin Fu, Yuefeng Bai, Baicheng Pan, Zhunga Liu 외 arxiv

Adversarial attacks against large vision-language models (LVLMs) serve as an effective means of assessing their robustness in cross-modal semantic understanding. Existing studies mainly focus on corrupting visual inputs …

Adversarial Attack

GuardianAgentBench: Where Agents Fail and How to Guard Them

2026-07-23 · Vishal Ishwar Naik, Chenyu Xu, Donna Dong, Hussein Hassan 외 arxiv

As large language model agents increasingly operate autonomously with access to tools and external environments, ensuring their safe and reliable behavior becomes critical. We present GuardianAgentBench (GABench), a benc…

Adversarial Attack

전체 1,998편 보기 →