Latest Adversarial Attack Papers

# Latest Adversarial Attack Papers
**update at 2026-01-19 16:16:59**

[中英双语版本](https://github.com/daksim/NewAdversarialAttackPaper/blob/main/README_CN.md)

[Attacks and Defenses in Large language Models](https://github.com/daksim/NewAdversarialAttackPaper/blob/main/README_LLM.md)

## **1. QUPID: A Partitioned Quantum Neural Network for Anomaly Detection in Smart Grid**

cs.LG

**SubmitDate**: 2026-01-16    [abs](http://arxiv.org/abs/2601.11500v1) [paper-pdf](https://arxiv.org/pdf/2601.11500v1)

**Authors**: Hoang M. Ngo, Tre' R. Jeter, Jung Taek Seo, My T. Thai

**Abstract**: Smart grid infrastructures have revolutionized energy distribution, but their day-to-day operations require robust anomaly detection methods to counter risks associated with cyber-physical threats and system faults potentially caused by natural disasters, equipment malfunctions, and cyber attacks. Conventional machine learning (ML) models are effective in several domains, yet they struggle to represent the complexities observed in smart grid systems. Furthermore, traditional ML models are highly susceptible to adversarial manipulations, making them increasingly unreliable for real-world deployment. Quantum ML (QML) provides a unique advantage, utilizing quantum-enhanced feature representations to model the intricacies of the high-dimensional nature of smart grid systems while demonstrating greater resilience to adversarial manipulation. In this work, we propose QUPID, a partitioned quantum neural network (PQNN) that outperforms traditional state-of-the-art ML models in anomaly detection. We extend our model to R-QUPID that even maintains its performance when including differential privacy (DP) for enhanced robustness. Moreover, our partitioning framework addresses a significant scalability problem in QML by efficiently distributing computational workloads, making quantum-enhanced anomaly detection practical in large-scale smart grid environments. Our experimental results across various scenarios exemplifies the efficacy of QUPID and R-QUPID to significantly improve anomaly detection capabilities and robustness compared to traditional ML approaches.



## **2. Backdoor Attacks on Multi-modal Contrastive Learning**

cs.LG

**SubmitDate**: 2026-01-16    [abs](http://arxiv.org/abs/2601.11006v1) [paper-pdf](https://arxiv.org/pdf/2601.11006v1)

**Authors**: Simi D Kuniyilh, Rita Machacy

**Abstract**: Contrastive learning has become a leading self- supervised approach to representation learning across domains, including vision, multimodal settings, graphs, and federated learning. However, recent studies have shown that contrastive learning is susceptible to backdoor and data poisoning attacks. In these attacks, adversaries can manipulate pretraining data or model updates to insert hidden malicious behavior. This paper offers a thorough and comparative review of backdoor attacks in contrastive learning. It analyzes threat models, attack methods, target domains, and available defenses. We summarize recent advancements in this area, underline the specific vulnerabilities inherent to contrastive learning, and discuss the challenges and future research directions. Our findings have significant implications for the secure deployment of systems in industrial and distributed environments.



## **3. AJAR: Adaptive Jailbreak Architecture for Red-teaming**

cs.CR

**SubmitDate**: 2026-01-16    [abs](http://arxiv.org/abs/2601.10971v1) [paper-pdf](https://arxiv.org/pdf/2601.10971v1)

**Authors**: Yipu Dou, Wang Yang

**Abstract**: As Large Language Models (LLMs) evolve from static chatbots into autonomous agents capable of tool execution, the landscape of AI safety is shifting from content moderation to action security. However, existing red-teaming frameworks remain bifurcated: they either focus on rigid, script-based text attacks or lack the architectural modularity to simulate complex, multi-turn agentic exploitations. In this paper, we introduce AJAR (Adaptive Jailbreak Architecture for Red-teaming), a proof-of-concept framework designed to bridge this gap through Protocol-driven Cognitive Orchestration. Built upon the robust runtime of Petri, AJAR leverages the Model Context Protocol (MCP) to decouple adversarial logic from the execution loop, encapsulating state-of-the-art algorithms like X-Teaming as standardized, plug-and-play services. We validate the architectural feasibility of AJAR through a controlled qualitative case study, demonstrating its ability to perform stateful backtracking within a tool-use environment. Furthermore, our preliminary exploration of the "Agentic Gap" reveals a complex safety dynamic: while tool usage introduces new injection vectors via code execution, the cognitive load of parameter formatting can inadvertently disrupt persona-based attacks. AJAR is open-sourced to facilitate the standardized, environment-aware evaluation of this emerging attack surface. The code and data are available at https://github.com/douyipu/

... (truncated)