English
Related papers

Related papers: On the Computation of Worst Attacks: a LP Framewor…

200 papers

Adversarial attacks on stochastic bandits have traditionally relied on some unrealistic assumptions, such as per-round reward manipulation and unbounded perturbations, limiting their relevance to real-world systems. We propose a more…

Machine Learning · Computer Science 2026-05-08 Qirun Zeng , Eric He , Richard Hoffmann , Xuchuang Wang , Jinhang Zuo

LLM developers have imposed technical interventions to prevent fine-tuning misuse attacks, attacks where adversaries evade safeguards by fine-tuning the model using a public API. Previous work has established several successful attacks…

Machine Learning · Computer Science 2025-10-27 Xander Davies , Eric Winsor , Alexandra Souly , Tomek Korbak , Robert Kirk , Christian Schroeder de Witt , Yarin Gal

In this paper, we consider the optimal controller design problem against data injection attacks on actuators for an uncertain control system. We consider attacks that aim at maximizing the attack impact while remaining stealthy in the…

Optimization and Control · Mathematics 2022-09-09 Sribalaji C. Anand , André M. H. Teixeira

The problem of mitigating maliciously injected signals in interconnected systems is dealt with in this paper. We consider the class of covert attacks, as they are stealthy and cannot be detected by conventional means in centralized…

Systems and Control · Electrical Eng. & Systems 2021-04-15 Angelo Barboni , Thomas Parisini

Sparse attacks are to optimize the magnitude of adversarial perturbations for fooling deep neural networks (DNNs) involving only a few perturbed pixels (i.e., under the l0 constraint), suitable for interpreting the vulnerability of DNNs.…

Machine Learning · Computer Science 2025-06-24 Fudong Lin , Jiadong Lou , Hao Wang , Brian Jalaian , Xu Yuan

Local differential privacy (LDP) involves users perturbing their inputs to provide plausible deniability of their data. However, this also makes LDP vulnerable to poisoning attacks. In this paper, we first introduce novel poisoning attacks…

Cryptography and Security · Computer Science 2025-07-01 Pei Zhan , Peng Tang , Yangzhuo Li , Puwen Wei , Shanqing Guo

We illustrate how computer-aided methods can be used to investigate the fundamental limits of the caching systems, which are significantly different from the conventional analytical approach usually seen in the information theory…

Information Theory · Computer Science 2018-08-28 Chao Tian

Federated learning (FL) combined with local differential privacy (LDP) enables privacy-preserving model training across decentralized data sources. However, the decentralized data-management paradigm leaves LDPFL vulnerable to participants…

Cryptography and Security · Computer Science 2025-09-08 Zijian Wang , Wei Tong , Tingxuan Han , Haoyu Chen , Tianling Zhang , Yunlong Mao , Sheng Zhong

This paper considers the problem of detector tuning against false data injection attacks. In particular, we consider an adversary injecting false sensor data to maximize the state deviation of the plant, referred to as impact, whilst being…

Systems and Control · Electrical Eng. & Systems 2026-01-15 Sribalaji C. Anand , Kamil Hassan , Henrik Sandberg

Defenses against security threats have been an interest of recent studies. Recent works have shown that it is not difficult to attack a natural language processing (NLP) model while defending against them is still a cat-mouse game. Backdoor…

Cryptography and Security · Computer Science 2022-05-31 Sangeet Sagar , Abhinav Bhatt , Abhijith Srinivas Bidaralli

Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison. Existing poisoning attacks primarily rely on fixed trigger phrases that defenses such as outlier detection, clean-data regularization,…

Cryptography and Security · Computer Science 2026-05-27 Zedian Shao , Charles Fleming , Teodora Baluta

In this paper, we study the resilience of process systems in an {\it information-theoretic framework}, from the perspective of an attacker capable of optimally constructing data injection attacks. The attack aims to distract the stationary…

Systems and Control · Electrical Eng. & Systems 2025-05-21 Xiuzhen Ye , Wentao Tang

Today's high-stakes adversarial interactions feature attackers who constantly breach the ever-improving security measures. Deception mitigates the defender's loss by misleading the attacker to make suboptimal decisions. In order to formally…

Artificial Intelligence · Computer Science 2020-06-11 Zheyuan Ryan Shi , Ariel D. Procaccia , Kevin S. Chan , Sridhar Venkatesan , Noam Ben-Asher , Nandi O. Leslie , Charles Kamhoua , Fei Fang

The generation of feasible adversarial examples is necessary for properly assessing models that work in constrained feature space. However, it remains a challenging task to enforce constraints into attacks that were designed for computer…

Artificial Intelligence · Computer Science 2022-05-04 Thibault Simonetto , Salijona Dyrmishi , Salah Ghamizi , Maxime Cordy , Yves Le Traon

Typical behavior of the linear programming problem (LP) is studied as a relaxation of the minimum vertex cover problem, which is a type of the integer programming problem (IP). To deal with the LP and IP by statistical mechanics, a…

Disordered Systems and Neural Networks · Physics 2014-03-31 Satoshi Takabe , Koji Hukushima

In [1], the distributed linear-quadratic problem with fixed communication topology (DFT-LQ) and the sparse feedback LQ problem (SF-LQ) are formulated into a nonsmooth and nonconvex optimization problem with affine constraints. Moreover, a…

Optimization and Control · Mathematics 2025-08-14 Lechen Feng , Xun Li , Yuan-Hua Ni

Trajectory data, which tracks movements through geographic locations, is crucial for improving real-world applications. However, collecting such sensitive data raises considerable privacy concerns. Local differential privacy (LDP) offers a…

Cryptography and Security · Computer Science 2025-03-11 I-Jung Hsu , Chih-Hsun Lin , Chia-Mu Yu , Sy-Yen Kuo , Chun-Ying Huang

As penetration testing frameworks have evolved and have become more complex, the problem of controlling automatically the pentesting tool has become an important question. This can be naturally addressed as an attack planning problem.…

Cryptography and Security · Computer Science 2017-07-10 Carlos Sarraute , Gerardo Richarte , Jorge Lucangeli Obes

Given a stable linear time-invariant (LTI) system subject to output constraints, we present a method to compute a set of disturbances such that the reachable set of outputs matches as closely as possible the output constraint set, while…

Systems and Control · Electrical Eng. & Systems 2023-10-10 Sampath Kumar Mulagaleti , Alberto Bemporad , Mario Zanon

This paper is concerned with understanding and countering the effects of database attacks on a learning-based linear quadratic adaptive controller. This attack targets neither sensors nor actuators, but just poisons the learning algorithm…

Systems and Control · Electrical Eng. & Systems 2022-11-08 Jafar Abbaszadeh Chekan , Cedric Langbort