paper-with-me

홈 › Papers

Adversarial Intent is a Latent Variable: Stateful Trust Inference for Securing Multimodal Agentic RAG

2026-02-24 · Inderjeet Singh, Vikas Pahuja, Aishvariya Priya Rathina Sabapathy, Chiara Picardi, Amit Giloni, Roman Vainshtein, Andrés Murillo, Hisashi Kojima, Motoyoshi Sekiya, Yuki Unno, Junichi Suga arxiv

Current stateless defences for multimodal agentic RAG fail to detect adversarial strategies that distribute malicious semantics across retrieval, planning, and generation components. We formulate this security challenge as a Partially Observable Markov Decision Process (POMDP), where adversarial intent is a latent variable inferred from noisy multi-stage observations. We introduce MMA-RAG^T, an inference-time control framework governed by a Modular Trust Agent (MTA) that maintains an approximate belief state via structured LLM reasoning. Operating as a model-agnostic overlay, MMA-RAGT mediates a configurable set of internal checkpoints to enforce stateful defence-in-depth. Extensive evaluation on 43,774 instances demonstrates a 6.50x average reduction factor in Attack Success Rate relative to undefended baselines, with negligible utility cost. Crucially, a factorial ablation validates our theoretical bounds: while statefulness and spatial coverage are individually necessary (26.4 pp and 13.6 pp gains respectively), stateless multi-point intervention can yield zero marginal benefit under homogeneous stateless filtering when checkpoint detections are perfectly correlated.

📄 PDF Abstract BibTeX arXiv:2602.21447

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning

2026-04-30 · Bowen Sun, Chaozhuo Li, Yaodong Yang, Yiwei Wang 외 arxiv

Decompositional jailbreaks pose a critical threat to large language models (LLMs) by allowing adversaries to fragment a malicious objective into a sequence of individually benign queries that collectively reconstruct pro…

Contrastive Learning

DeepContext: Stateful Real-Time Detection of Multi-Turn Adversarial Intent Drift in LLMs

2026-02-18 · Justin Albrethsen, Yash Datta, Kunal Kumar, Sharath Rajasekar arxiv

While Large Language Model (LLM) capabilities have scaled, safety guardrails remain largely stateless, treating multi-turn dialogues as a series of disconnected events. This lack of temporal awareness facilitates a "Safe…

Adversarially Guided Stateful Defense Against Backdoor Attacks in Federated Deep Learning

2024-10-15 · Hassan Ali, Surya Nepal, Salil S. Kanhere, Sanjay Jha

Recent works have shown that Federated Learning (FL) is vulnerable to backdoor attacks. Existing defenses cluster submitted updates from clients and select the best cluster for aggregation. However, they often rely on un…

Federated Learning

Adversarial Domain Adaptation for Stable Brain-Machine Interfaces

2018-09-28 · ICLR 2019 5 · Ali Farshchian, Juan A. Gallego, Joseph P. Cohen, Yoshua Bengio 외

Brain-Machine Interfaces (BMIs) have recently emerged as a clinically viable option to restore voluntary movements after paralysis. These devices are based on the ability to extract information about movement intent from…

Domain AdaptationTime Series Analysis

Intent Contrastive Learning for Sequential Recommendation

2022-02-05 · Yongjun Chen, Zhiwei Liu, Jia Li, Julian McAuley 외

Users' interactions with items are driven by various intents (e.g., preparing for holiday gifts, shopping for fishing equipment, etc.).However, users' underlying intents are often unobserved/latent, making it challenging…

Contrastive LearningModel OptimizationRepresentation LearningSelf-Supervised Learning+1