Related papers: Semantic Security with Unreliable Entanglement Ass…

In secure network coding, there is a possibility that the eavesdropper can improve her performance when she changes (contaminates) the information on the attacked edges (active attack) and chooses the attacked edges adaptively (adaptive…

Recently, semantically constrained adversarial examples (SemanticAE), which are directly generated from natural language instructions, have become a promising avenue for future research due to their flexible attacking forms. To generate…

Despite significant advancements in computer vision, semantic segmentation models may be susceptible to backdoor attacks. These attacks, involving hidden triggers, aim to cause the models to misclassify instances of the victim class as the…

Software vulnerabilities (SVs) have emerged as a prevalent and critical concern for safety-critical security systems. This has spurred significant advancements in utilizing AI-based methods, including machine learning and deep learning, for…

We consider a setting of non-cooperative communication where a receiver wants to recover randomly generated sequences of symbols that are observed by a strategic sender. The sender aims to maximize an average utility that may not align with…

We consider a source-destination pair that can only communicate through an untrusted intermediate relay node. The intermediate node is willing to employ a designated relaying scheme to facilitate reliable communication between the source…

Machine learning (ML) models cannot neglect risks to security, privacy, and fairness. Several defenses have been proposed to mitigate such risks. When a defense is effective in mitigating one risk, it may correspond to increased or…

A new channel coding approach was proposed in [1] for random multiple access communication over the discrete-time memoryless channel. The coding approach allows users to choose their communication rates independently without sharing the…

Achieving robustness against adversarial input perturbation is an important and intriguing problem in machine learning. In the area of semantic image segmentation, a number of adversarial training approaches have been proposed as a defense…

We consider a system where an agent (Alice) aims at transmitting a message to a second agent (Bob) over a set of parallel channels, while keeping it secret from a third agent (Eve) by using physical layer security techniques. We assume that…

Detecting semantic backdoors in classification models--where some classes can be activated by certain natural, but out-of-distribution inputs--is an important problem that has received relatively little attention. Semantic backdoors are…

Surveillance performance is studied for a wireless eavesdropping system, where a full-duplex legitimate monitor eavesdrops a suspicious link efficiently with the artificial noise (AN) assistance. Different from the existing work in the…

We give a rigorous characterization of what it means for a programming language to be memory safe, capturing the intuition that memory safety supports local reasoning about state. We formalize this principle in two ways. First, we show how…

A novel secure communication protocol is presented, based on an entangled pair of qubits and allowing asymptotically secure key distribution and quasi-secure direct communication. Since the information is transferred in a deterministic…

Semantic communication aims to facilitate purposeful information exchange among diverse intelligent entities, including humans, machines, and organisms. It emphasizes precise semantic transmission over data fidelity, striving for meaningful…

Sampled semantics of timed automata is a finite approximation of their dense time behavior. While the former is closer to the actual software or hardware systems with a fixed granularity of time, the abstract character of the latter makes…

During the last years, large-scale simulations of realistic physical environments which support the interaction of multiple participants over the Internet have become increasingly available and economically significant, most notably in the…

We propose semantic entropy probes (SEPs), a cheap and reliable method for uncertainty quantification in Large Language Models (LLMs). Hallucinations, which are plausible-sounding but factually incorrect and arbitrary model generations,…

We formulate a model for intermittent communication that can capture bursty transmissions or a sporadically available channel, where in either case the receiver does not know a priori when the transmissions will occur. Focusing on the…

Semantic control entails steering LM generations towards satisfying subtle non-lexical constraints, e.g., toxicity, sentiment, or politeness, attributes that can be captured by a sequence-level verifier. It can thus be viewed as sampling…