Related papers: FOLPETTI: A Novel Multi-Armed Bandit Smart Attack …

Due to the broad range of applications of stochastic multi-armed bandit model, understanding the effects of adversarial attacks and designing bandit algorithms robust to attacks are essential for the safe applications of this model. In this…

Despite rigorous safety alignment, Large Language Models (LLMs) remain vulnerable to jailbreak attacks. Existing black-box methods often rely on heuristic templates or exhaustive trials, lacking mechanistic interpretability and query…

This work addresses a reactive jamming attack on the low-latency messages of a victim, wherein the jammer deploys countermeasure detection mechanisms to change its strategy. We highlight that the existing schemes against reactive jammers…

In this paper a new algorithm for adaptive dynamic channel estimation for frequency selective time varying fading OFDM channels is proposed. The new algorithm adopts a new strategy that successfully increases OFDM symbol rate. Instead of…

Large language models remain vulnerable to jailbreak attacks, yet we still lack a systematic understanding of how jailbreak success scales with attacker effort across methods, model families, and harm types. We initiate a scaling-law…

A recent line of research focuses on the study of the stochastic multi-armed bandits problem (MAB), in the case where temporal correlations of specific structure are imposed between the player's actions and the reward distributions of the…

Multi-armed bandit (MAB) problems are widely applied to online optimization tasks that require balancing exploration and exploitation. In practical scenarios, these tasks often involve multiple conflicting objectives, giving rise to…

Long range, low power networks are rapidly gaining acceptance in the Internet of Things (IoT) due to their ability to economically support long-range sensing and control applications while providing multi-year battery life. LoRa is a key…

To realize orthogonal frequency division multiplexing (OFDM)-based grant-free access for wideband systems under frequency-selective fading, existing device activity detection and channel estimation methods need substantial accuracy…

We present an approach to Intelligent Tutoring Systems which adaptively personalizes sequences of learning activities to maximize skills acquired by students, taking into account the limited time and motivational resources. At a given point…

In this paper, we explore the use of multi-armed bandit online learning techniques to solve distributed resource selection problems. As an example, we focus on the problem of network selection. Mobile devices often have several wireless…

Finetuning open-weight Large Language Models (LLMs) is standard practice for achieving task-specific performance improvements. Until now, finetuning has been regarded as a controlled and secure process in which training on benign datasets…

Suppressing the deliberate interference for wireless networks is critical to guarantee a reliable communication link. However, nullifying the jamming signals can be problematic when the correlations between transmitted jamming signals are…

We propose and study Collpasing Bandits, a new restless multi-armed bandit (RMAB) setting in which each arm follows a binary-state Markovian process with a special structure: when an arm is played, the state is fully observed, thus…

Federated learning (FL) enables privacy-preserving model training by keeping data decentralized. However, it remains vulnerable to label-flipping attacks, where malicious clients manipulate labels to poison the global model. Despite their…

In modern ML Ops environments, model deployment is a critical process that traditionally relies on static heuristics such as validation error comparisons and A/B testing. However, these methods require human intervention to adapt to…

With conventional anti-jamming solutions like frequency hopping or spread spectrum, legitimate transceivers often tend to "escape" or "hide" themselves from jammers. These reactive anti-jamming approaches are constrained by the lack of…

Federated learning (FL) offers a decentralized learning environment so that a group of clients can collaborate to train a global model at the server, while keeping their training data confidential. This paper studies how to launch…

In this paper, we investigate the design of a burst jamming detection method for delay-sensitive Internet-of-Things (IoT) applications. In order to obtain a timely detection of burst jamming, we propose an online principal direction anomaly…

Security attacks at the physical layer, in the form of radio jamming for denial of service, are an increasing threat in the Industry 4.0 scenarios. In this paper, we consider the problem of jamming detection in 5G-and-beyond communication…