Related papers: Worst case attacks against binary probabilistic tr…

In security-sensitive applications, the success of machine learning depends on a thorough vetting of their resistance to adversarial data. In one pertinent, well-motivated attack scenario, an adversary may attempt to evade a deployed system…

Motivated by the importance of explainability in modern machine learning, we design bandit algorithms that are efficient and interpretable. A bandit algorithm is interpretable if it explores with the objective of reducing uncertainty in the…

Recently, advanced NLP models have seen a surge in the usage of various applications. This raises the security threats of the released models. In addition to the clean models' unintentional weaknesses, {\em i.e.,} adversarial attacks, the…

We consider the problem of false data injection attacks modeled as additive disturbances in various parts of a general LTI feedback system and derive necessary and sufficient conditions for the existence of stealthy unbounded attacks. We…

Machine learning algorithms, however effective, are known to be vulnerable in adversarial scenarios where a malicious user may inject manipulated instances. In this work we focus on evasion attacks, where a model is trained in a safe…

Backdoor attacks (BAs) are an emerging threat to deep neural network classifiers. A victim classifier will predict to an attacker-desired target class whenever a test sample is embedded with the same backdoor pattern (BP) that was used to…

In recent work, we have introduced a framework for fine-grained consent management in databases, which combines Boolean data provenance with the field of interactive Boolean evaluation. In turn, interactive Boolean evaluation aims at…

In recent years, large language models (LLMs) have made significant progress in the field of code generation. However, as more and more users rely on these models for software development, the security risks associated with code generation…

In the worst-case analysis of algorithms, the overall performance of an algorithm is summarized by its worst performance on any input. This approach has countless success stories, but there are also important computational problems --- like…

In this work, we introduce a framework to study the effect of random operations on the combinatorial list-decodability of a code. The operations we consider correspond to row and column operations on the matrix obtained from the code by…

Trajectory planning is a key piece in the algorithmic architecture of a robot. Trajectory planners typically use iterative optimization schemes for generating smooth trajectories that avoid collisions and are optimal for tracking given the…

In this work, we consider two types of adversarial attacks on a network of nodes seeking to reach consensus. The first type involves an adversary that is capable of breaking a specific number of links at each time instant. In the second…

While progress has been made in understanding the robustness of machine learning classifiers to test-time adversaries (evasion attacks), fundamental questions remain unresolved. In this paper, we use optimal transport to characterize the…

As deep neural networks and the datasets used to train them get larger, the default approach to integrating them into research and commercial projects is to download a pre-trained model and fine tune it. But these models can have uncertain…

We study the secrecy capacity in the vicinity of colluding eavesdroppers. Contrary to the perfect collusion assumption in previous works, our new information-theoretic model considers constraints in collusion. We derive the achievable…

We quantify the threat of network adversaries to inducing \emph{network overload} through \emph{routing attacks}, where a subset of network nodes are hijacked by an adversary. We develop routing attacks on the hijacked nodes for two…

In recent years, deep neural networks demonstrated state-of-the-art performance in a large variety of tasks and therefore have been adopted in many applications. On the other hand, the latest studies revealed that neural networks are…

As pairwise ranking becomes broadly employed for elections, sports competitions, recommendations, and so on, attackers have strong motivation and incentives to manipulate the ranking list. They could inject malicious comparisons into the…

We consider the problem of block-coded communication, where in each block, the channel law belongs to one of two disjoint sets. The decoder is aimed to decode only messages that have undergone a channel from one of the sets, and thus has to…

Error-correcting codes and related combinatorial constructs play an important role in several recent (and old) results in computational complexity theory. In this paper we survey results on locally-testable and locally-decodable…