❌

Normal view

Received β€” 10 September 2026 ⏭

AgentHijack: Visual Patch Attacks on Multimodal Computer-Use Agents

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Zhihao Liu Β· Hongyu Sun Β· Zhiyuan Fu Β· Xiaonan Duan Β· Jice Wang Β· Shangru Zhao Β· Weizhi Meng Β· Wuxin Yang Β· Yangfan Zhou Β· Yuqing Zhang
10 September 2026 at 12:00
arXiv:2609.09212v1 Announce Type: cross Abstract: This paper presents an end-to-end evaluation framework for image-triggered command injection against computer-use agents (CUAs). The goal is to test whether a local visual patch can induce verifiable environmental consequences along the full chain of screenshot input, VLM generation, action parsing, and environment execution. We train and deploy patches on author-controlled GitHub Pages pages and a locally deployed CSDN clone, and evaluate them in real environments across five open-source or publicly available GUI-agent or vision-language-model (VLM) backends. Our experiment aggregates 600 instance-level online cases, with T-ASR, TAPR, and E2E-ASR reaching 84.5%, 47.0%, and 20.3%, respectively. Trajectory analysis further shows that in some successful cases the agent first executes a malicious terminal command and then continues the original benign task. These results indicate that optimized local visual signals can affect not only VLM outputs but also propagate through the execution pipeline of open CUAs and create real environmental risk.

Targeting KRAS reprograms a Treg-dominant immunosuppressive microenvironment and sensitizes KRAS-mutant gastric adenocarcinoma to CTLA-4 immunotherapy

βœ‡(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Xiaohuan Tang Β· Peiyao Yang Β· Xiaoyong Guo Β· Shuhua Wei Β· Xiaojing Cheng Β· Mengyuan Li Β· Yigang Bao Β· Sachiyo Nomura Β· Yu Sun Β· Longtao Huangfu Β· Xiaofang Xing Β· Yongning Jia Β· Fei Shan Β· Xiangyu Gao Β· Chuanhui Han Β· Ziyu Li
9 September 2026 at 18:00

Sci China Life Sci. 2026 Sep 3. doi: 10.1007/s11427-026-3438-4. Online ahead of print.

ABSTRACT

Oncogenic KRAS mutations define a distinct molecular subset of gastric adenocarcinoma (GA), yet their impact on the tumor immune microenvironment remains incompletely understood. In this study, we established a genetically faithful and immunocompetent KRASG12D-driven mouse model of GA, together with matched organoids and cell lines, to investigate how oncogenic KRAS shapes tumor-immune interactions. KRAS-mutant tumors consistently developed an immunosuppressive microenvironment characterized by enrichment of regulatory T cells (Tregs), accompanied by reduced cytotoxic lymphocyte infiltration and intrinsic resistance to PD-1 blockade. Although pharmacologic targeting of KRAS effectively suppressed tumor growth and increased immune cell infiltration, functional immune analyses revealed persistent Treg-mediated immunosuppression that limited effective antitumor immunity. Mechanistically, TGF-Ξ² signaling was required to maintain Treg dominance and suppress effector T cell function in KRAS-driven tumors. Importantly, disruption of this suppressive axis through combined KRAS inhibition and CTLA-4 blockade attenuated TGF-Ξ² activity, impaired Treg function, and enhanced antitumor immune responses in vivo. Collectively, these findings identify oncogenic KRAS as a key regulator of TGF-Ξ²-dependent immune suppression in GA and provide mechanistic insight into immune evasion within this molecular subtype.

PMID:42714795 | DOI:10.1007/s11427-026-3438-4

There are no more articles
❌