arXiv subjects

Umesh Biswas

Publications and source records attributed to Umesh Biswas.

5 recordsLinked to original sources

arXiv2026

Attribution-Driven Explainable Intrusion Detection with Encoder-Based Large Language Models

Software-Defined Networking (SDN) improves network flexibility but also increases the need for reliable and interpretable intrusion detection. Large Language Models (LLMs) have recently been explored for cybersecurity tasks due to their strong representation learning capabilities; however, their lack of transparency limits their practical adoption in security-critical environments. Understanding how LLMs make decisions is therefore essential. This paper presents an attribution-driven analysis of encoder-based LLMs for network intrusion detection using flow-level traffic features. Attribution analysis demonstrates that model decisions are driven by meaningful traffic behavior patterns, improving transparency and trust in transformer-based SDN intrusion detection. These patterns align with established intrusion detection principles, indicating that LLMs learn attack behavior from traffic dynamics. This work demonstrates the value of attribution methods for validating and trusting LLM-based security analysis.

cs.CR↗

arXiv2025

Learning Robust Representations for Malicious Content Detection via Contrastive Sampling and Uncertainty Estimation

We propose the Uncertainty Contrastive Framework (UCF), a Positive-Unlabeled (PU) representation learning framework that integrates uncertainty-aware contrastive loss, adaptive temperature scaling, and a self-attention-guided LSTM encoder to improve classification under noisy and imbalanced conditions. UCF dynamically adjusts contrastive weighting based on sample confidence, stabilizes training using positive anchors, and adapts temperature parameters to batch-level variability. Applied to malicious content classification, UCF-generated embeddings enable multiple traditional classifiers to achieve more than 93.38% accuracy, precision above 0.93, and near-perfect recall, with minimal false negatives and competitive ROC-AUC scores. Visual analyses confirm clear separation between positive and unlabeled instances, highlighting the framework's ability to produce calibrated, discriminative embeddings. These results position UCF as a robust and scalable solution for PU learning in high-stakes domains such as cybersecurity and biomedical text mining.

cs.LG↗

arXiv2025

A Survey of Recent Advancements in Secure Peer-to-Peer Networks

Peer-to-peer (P2P) networks are a cornerstone of modern computing, and their security is an active area of research. Many defenses with strong security guarantees have been proposed; however, the most-recent survey is over a decade old. This paper delivers an updated review of recent theoretical advances that address classic threats, such as the Sybil and routing attacks, while highlighting how emerging trends -- such as machine learning, social networks, and dynamic systems -- pose new challenges and drive novel solutions. We evaluate the strengths and weaknesses of these solutions and suggest directions for future research.

cs.DC↗

arXiv2025

A Gentle Wakeup Call: Symmetry Breaking with Less Collision Cost

The wakeup problem addresses the fundamental challenge of symmetry breaking. Initially, n devices share a time-slotted multiple access channel, which models wireless communication. A transmission succeeds if exactly one device sends in a slot; if two or more transmit, a collision occurs and none succeed. The goal is to achieve a single successful transmission efficiently. Prior work on wakeup primarily analyzes latency -- the number of slots until the first success. However, in many modern systems, each collision incurs a nontrivial delay, C, which prior analyses neglect. Consequently, although existing algorithms achieve polylogarithmic-in-n latency, they still suffer a delay of \Omega(C) due to collisions. Here, we design and analyze a randomized wakeup algorithm, Aim-High. When C is sufficiently large with respect to n, Aim-High has expected latency and expected total cost of collisions that are nearly O(\sqrt{C}); otherwise, both quantities are O(poly{\log n}). Finally, for a well-studied class of algorithms, we establish a trade-off between latency and expected total cost of collisions.

cs.DS↗

arXiv2024

Softening the Impact of Collisions in Contention Resolution

Contention resolution addresses the problem of coordinating access to a shared communication channel. Time is discretized into synchronized slots, and a packet can be sent in any slot. If no packet is sent, then the slot is empty; if a single packet is sent, then it is successful; and when multiple packets are sent at the same time, a collision occurs, resulting in the failure of the corresponding transmissions. In each slot, every packet receives ternary channel feedback indicating whether the current slot is empty, successful, or a collision. Much of the prior work on contention resolution has focused on optimizing the makespan, which is the number of slots required for all packets to succeed. However, in many modern systems, collisions are also costly in terms of the time they incur, which existing contention-resolution algorithms do not address. In this paper, we design and analyze a randomized algorithm, Collision Aversion Backoff (CAB), that optimizes both the makespan and the collision cost. We consider the static case where an unknown $n\geq 2$ packets are initially present in the system, and each collision has a known cost $\mathcal{C}$, where $1 \leq \mathcal{C} \leq n^{\kappa}$ for a known constant $\kappa\geq 0$. With error probability polynomially small in $n$, CAB guarantees that all packets succeed with makespan and a total expected collision cost of $\tilde{O}(n\sqrt{\mathcal{C}})$. We give a lower bound for the class of fair algorithms: where, in each slot, every packet executing the fair algorithm sends with the same probability (and the probability may change from slot to slot). Our lower bound is asymptotically tight up to a $\texttt{poly}(\log n)$-factor for sufficiently large $\mathcal{C}$.

cs.DC↗