English
Related papers

Related papers: Semantic Security with Unreliable Entanglement Ass…

200 papers

Disentangled latent spaces usually have better semantic separability and geometrical properties, which leads to better interpretability and more controllable data generation. While this has been well investigated in Computer Vision, in…

Computation and Language · Computer Science 2024-06-12 Yingji Zhang , Danilo S. Carvalho , André Freitas

Learning disentangled representations that correspond to factors of variation in real-world data is critical to interpretable and human-controllable machine learning. Recently, concerns about the viability of learning disentangled…

Machine Learning · Computer Science 2020-04-14 Rui Shu , Yining Chen , Abhishek Kumar , Stefano Ermon , Ben Poole

An open problem for autonomous driving is how to validate the safety of an autonomous vehicle in simulation. Automated testing procedures can find failures of an autonomous system but these failures may be difficult to interpret due to…

Robotics · Computer Science 2020-06-29 Anthony Corso , Mykel J. Kochenderfer

We determine the optimal achievable rate at which entanglement can be reliably transmitted when the memoryless channel used during transmission is unknown both to sender and receiver. To be more precise, we assume that both of them only…

Quantum Physics · Physics 2009-04-21 Igor Bjelakovic , Holger Boche , Janis Noetzel

Artificial intelligence (AI) is ushering in a new era for communication. As a result, the establishment of a semantic communication framework is putting on the agenda. Based on a realistic semantic communication model, this paper develops a…

Information Theory · Computer Science 2025-09-15 Yi-Qun Zhao , Zhi-Ming Ma , Geoffrey Ye Li , Shuai Yuan , Tong Ye , Chuan Zhou

Semantic communication (SemCom) has emerged as a promising paradigm for next-generation networks. However, its typical end-to-end joint source--channel coding (JSCC) architecture also raises serious privacy concerns. To guide future secure…

Signal Processing · Electrical Eng. & Systems 2026-05-11 Shunpu Tang , Qianqian Yang , Zhiguo Shi , Jiming Chen , Xuemin Shen

Semantic communication has been identified as a core technology for the sixth generation (6G) of wireless networks. Recently, task-oriented semantic communications have been proposed for low-latency inference with limited bandwidth.…

Information Theory · Computer Science 2023-12-07 Yanhu Wang , Shuaishuai Guo , Yiqin Deng , Haixia Zhang , Yuguang Fang

Predictive maintenance in complex systems is often complicated by the heterogeneity and redundancy of monitored variables,which can obscure fault-relevant information and reduce model interpretability. This work proposes a semantic feature…

Artificial Intelligence · Computer Science 2026-05-15 Emilio Mastriani , Alessandro Costa , Federico Incardona , Kevin Munari , Sebastiano Spinello

The zeitgeist of the digital era has been dominated by an expanding integration of Artificial Intelligence~(AI) in a plethora of applications across various domains. With this expansion, however, questions of the safety and reliability of…

Artificial Intelligence · Computer Science 2023-12-19 Al-Harith Farhad , Ioannis Sorokos , Mohammed Naveed Akram , Koorosh Aslansefat , Daniel Schneider

With the widespread application of Large Language Models (LLMs) to various domains, concerns regarding the trustworthiness of LLMs in safety-critical scenarios have been raised, due to their unpredictable tendency to hallucinate and…

Computation and Language · Computer Science 2024-11-04 Xin Qiu , Risto Miikkulainen

With the exponential surge in traffic data and the pressing need for ultra-low latency in emerging intelligence applications, it is envisioned that 6G networks will demand disruptive communication technologies to foster ubiquitous…

Information Theory · Computer Science 2024-08-12 Youlong Wu , Yuanmin Shi , Shuai Ma , Chunxiao Jiang , Wei Zhang , Khaled B. Letaief

Responsible deployment of language models requires mechanisms for refusing unsafe prompts while preserving model performance. While most approaches modify model weights through additional training, we explore an alternative: steering model…

When users work with AI agents, they form conscious or subconscious expectations of them. Meeting user expectations is crucial for such agents to engage in successful interactions and teaming. However, users may form expectations of an…

Artificial Intelligence · Computer Science 2025-09-26 Akkamahadevi Hanni , Jonathan Montaño , Yu Zhang

Memory-safety issues and information leakage are known to be depressingly common. We consider the compositional static detection of these kinds of vulnerabilities in first-order C-like programs. Indeed the latter are relational hyper-safety…

Programming Languages · Computer Science 2023-08-22 Toby Murray , Pengbo Yan , Gidon Ernst

Large language models (LLMs) are widely used for task understanding and action planning in embodied intelligence (EI) systems, but their adoption substantially increases vulnerability to jailbreak attacks. While recent work explores…

Cryptography and Security · Computer Science 2026-01-06 Jirui Yang , Zheyu Lin , Zhihui Lu , Yinggui Wang , Lei Wang , Tao Wei , Qiang Duan , Xin Du , Shuhan Yang

In a dynamic environment, an agent with a limited field of view/resource cannot fully observe the scene before attempting to parse it. The deployment of common semantic segmentation architectures is not feasible in such settings. In this…

Computer Vision and Pattern Recognition · Computer Science 2020-07-23 Soroush Seifi , Tinne Tuytelaars

We study the problem of entity-relation extraction in the presence of symbolic domain knowledge. Such knowledge takes the form of an ontology defining relations and their permissible arguments. Previous approaches set out to integrate such…

Machine Learning · Computer Science 2021-03-23 Kareem Ahmed , Eric Wang , Guy Van den Broeck , Kai-Wei Chang

Distantly supervised relation extraction intrinsically suffers from noisy labels due to the strong assumption of distant supervision. Most prior works adopt a selective attention mechanism over sentences in a bag to denoise from wrongly…

Computation and Language · Computer Science 2019-11-28 Yang Li , Guodong Long , Tao Shen , Tianyi Zhou , Lina Yao , Huan Huo , Jing Jiang

Weakly-supervised temporal action localization is a problem of learning an action localization model with only video-level action labeling available. The general framework largely relies on the classification activation, which employs an…

Computer Vision and Pattern Recognition · Computer Science 2020-03-31 Baifeng Shi , Qi Dai , Yadong Mu , Jingdong Wang

The debate around the interpretability of attention mechanisms is centered on whether attention scores can be used as a proxy for the relative amounts of signal carried by sub-components of data. We propose to study the interpretability of…

Machine Learning · Computer Science 2022-07-27 Jonathan Haab , Nicolas Deutschmann , Maria Rodríguez Martínez