Benchmarking Web Agent Safety under E-commerce Deceptive Interfaces (2026.acl-long)
Copied to clipboard
| Challenge: | Existing web agents are highly susceptible to multiple classes of deceptive interfaces, but they are not designed to mitigate these failures. |
| Approach: | They propose a lightweight plugin framework that allows controlled injection of deceptive interface patterns into existing web environments. |
| Outcome: | The proposed framework enables controlled injection of deceptive interface patterns into web environments. |
Similar Papers
A Functionality-Grounded Benchmark for Evaluating Web Agents in E-commerce Domains (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks focus on product search tasks, but ignore potential risks. |
| Approach: | They propose a data generation pipeline that leverages webpage content and interactive elements to create diverse, functionality-grounded user queries. |
| Outcome: | The proposed framework assesses the performance and safety of web agents under dynamic, real-world e-commerce environments. |
Don’t Click That: Teaching Web Agents to Resist Deceptive Interfaces (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to deception detection and defenses are inadequate . Existing methods do not integrate with agent decision-making . |
| Approach: | They propose a framework that integrates hybrid-reward learning with asymmetric penalties and experience summarization to distill failure patterns into transferable guidance. |
| Outcome: | The proposed framework reduces deception susceptibility by 53.8% while maintaining task performance, establishing an effective foundation for robust web agent deployment. |
RISK: A Framework for GUI Agents in E-commerce Risk Management (2026.acl-long)
Copied to clipboard
Renqi Chen, Zeyin Tao, Jianming Guo, Jingzhe Zhu, Yiheng Peng, Qingqing Sun, Tianyi Zhang, Shuai Chen
| Challenge: | RISK is a framework designed to automate multi-step web interactions in e-commerce risk management. |
| Approach: | a new framework is designed to build and deploy GUI agents for e-commerce risk management . RISK-R1 provides a scalable, domain-specific solution for automating complex web interactions . |
| Outcome: | RISK provides a scalable, domain-specific solution for automating complex web interactions in e-commerce risk management. |
Web Fraud Attacks Against LLM-Driven Multi-Agent Systems (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Model (LLM)-driven multi-agent systems (MAS) are rapidly gaining popularity, and its inherent security risks are rapidly becoming a concern. |
| Approach: | They propose a novel attack manipulating unique structures of web links to deceive MAS by using homoglyph deception, sub-directory nesting, and parameter obfuscation. |
| Outcome: | The proposed attacks exploit unique structures of web links to deceive MAS . they exhibit significant destructive potential across different MAS architectures . |
ECom-Bench: Can LLM Agent Resolve Real-World E-commerce Customer Support Issues? (2025.emnlp-industry)
Copied to clipboard
| Challenge: | ECom-Bench is a benchmark framework for evaluating LLM agent with multimodal capabilities in e-commerce customer support domain. |
| Approach: | They introduce a benchmark framework for evaluating LLM agent with multimodal capabilities in the e-commerce customer support domain. |
| Outcome: | The proposed benchmark features dynamic user simulation based on persona information from real e-commerce customer interactions and a realistic task dataset derived from authentic ecommerce dialogues. |
Conjunctive Prompt Attacks in Multi-Agent LLM Systems (2026.acl-long)
Copied to clipboard
| Challenge: | Existing defenses do not reliably stop the attack because no single component appears malicious in isolation. |
| Approach: | They study conjunctive prompt attacks where trigger key and adversarial template appear benign alone but activate harmful behavior when routing brings them together. |
| Outcome: | The proposed model significantly improves performance over baselines while keeping false activations low. |
The Dangers of Indirect Prompt Injection Attacks on LLM-based Autonomous Web Navigation Agents: A Demonstration (2025.emnlp-demos)
Copied to clipboard
| Challenge: | Large Language Model (LLM)-integrated applications are becoming more popular to support, augment, and automate tasks. |
| Approach: | They propose to embed universal adversarial triggers in webpage HTML to hijack agents . they also use a browser-gym agent powered by Llama-3.1 to test their system . |
| Outcome: | The proposed system software is released under the MIT License . |
WebOlympus: An Open Platform for Web Agents on Live Websites (2024.emnlp-demo)
Copied to clipboard
| Challenge: | Web agents are emerging as powerful tools for automating tasks in cyberspace . however, there is a lack of standardized and user-friendly tools for research and development . |
| Approach: | They propose an open platform for web agents operating on live websites with a Chrome extension and a safety monitor module to ensure their trustworthiness. |
| Outcome: | WebOlympus is an open platform for web agents operating on live websites. |
Agent-Ops: A Multi-Agent Orchestration Framework for End-to-End SOP Automation in E-Commerce Operations (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing Large Language Models fail to execute multistep operational workflows requiring precise procedural adherence. |
| Approach: | They propose an end-to-end multi-agent framework automating Standard Operating Procedures in e-commerce. |
| Outcome: | The proposed framework achieves 85-97% accuracy and a 94.2% execution consistency in e-commerce . it is based on a human-AI framework that transforms ambiguous documentation into automation-ready specifications . |
Multimodal Safety Evaluation in Generative Agent Social Simulations (2026.acl-long)
Copied to clipboard
Alhim Adonai Vera Gonzalez, Carlos Hinojosa, Karen Sanchez, Haidar Bin Hamid, Donghoon Kim, Bernard Ghanem
| Challenge: | Recent advances in large language models have enabled generative agents that simulate be-like behavior through natural language interactions. |
| Approach: | They propose a reproducible simulation framework to evaluate generative agents in multimodal scenarios . they use metrics that quantify plan revisions and unsafe-to-safe conversions to evaluate their effectiveness . |
| Outcome: | The proposed framework evaluates generative agents in three aspects: safety improvement over time, detection of unsafe activities across social contexts, social dynamics and acceptance rates. |