Related papers: Black Box White Arrow
We show how semiclassical black holes can be reinterpreted as an effective geometry, composed of a large ensamble of horizonless naked singularities (eventually smoothed at the Planck scale). We call this new items {\it frizzyballs}, which…
Note that this paper is superceded by "Black-Box Adversarial Attacks with Limited Queries and Information." Current neural network-based image classifiers are susceptible to adversarial examples, even in the black-box setting, where the…
Unlike the white-box counterparts that are widely studied and readily accessible, adversarial examples in black-box settings are generally more Herculean on account of the difficulty of estimating gradients. Many methods achieve the task by…
Solving for adversarial examples with projected gradient descent has been demonstrated to be highly effective in fooling the neural network based classifiers. However, in the black-box setting, the attacker is limited only to the query…
Capture calculus has recently been proposed as a solution to effect checking, achieved by tracking the captured references of terms in the types. Boxes, along with the box and unbox operations, are a crucial construct in capture calculus,…
Generalizing classical extension theory, we solve a Schreier-type extension problem for polygroups by groups. As a consequence, we obtain a method for computing a presentation for a group from its action on a set. The usefulness of this…
In this paper, we propose a brand new public key encryption scheme in the Lie group that is a non-abelian group. In particular, we firstly investigate the intractability assumptions in the Lie group, including the non-abelian factoring…
Shamir or Blakley secret sharing schemes are used for the authentication process in the studies before, but still secure group authentication and hand-over process remain as challenges in group authentication approaches. In this study, a…
Black-box adversarial attacks have demonstrated strong potential to compromise machine learning models by iteratively querying the target model or leveraging transferability from a local surrogate model. Recently, such attacks can be…
Quantum algorithms for factoring and discrete logarithm have previously been generalized to finding hidden subgroups of finite Abelian groups. This paper explores the possibility of extending this general viewpoint to finding hidden…
This is a study of the MOR cryptosystem using the special linear group over finite fields. The automorphism group of the special linear group is analyzed for this purpose. At our current state of knowledge, I show that the MOR cryptosystem…
Neural networks have emerged as powerful tools across various applications, yet their decision-making process often remains opaque, leading to them being perceived as "black boxes." This opacity raises concerns about their interpretability…
Large Language Models are increasingly adopted as critical tools for accelerating innovation. This paper identifies and formalizes a systemic risk inherent in this paradigm: \textbf{Black Box Absorption}. We define this as the process by…
We construct a classical oracle relative to which $\mathsf{P} = \mathsf{NP}$ yet single-copy secure pseudorandom quantum states exist. In the language of Impagliazzo's five worlds, this is a construction of pseudorandom states in…
Adversarial attack methods for 3D point cloud classification reveal the vulnerabilities of point cloud recognition models. This vulnerability could lead to safety risks in critical applications that use deep learning models, such as…
While efficient algorithms are known for solving many important problems related to groups, no efficient algorithm is known for determining whether two arbitrary groups are isomorphic. The particular case of 2-nilpotent groups, a special…
We propose a novel eXplainable AI algorithm to compute faithful, easy-to-understand, and complete global decision rules from local explanations for tabular data by combining XAI methods with closed frequent itemset mining. Our method can be…
Deep neural networks are vulnerable to adversarial attacks. White-box adversarial attacks can fool neural networks with small adversarial perturbations, especially for large size images. However, keeping successful adversarial perturbations…
We develop a generalized framework for invariant-based cryptography by extending the use of structural identities as core cryptographic mechanisms. Starting from a previously introduced scheme where a secret is encoded via a four-point…
General cryptographic schemes are presented where keys can be one-time or ephemeral. Processes for key exchange are derived. Public key cryptographic schemes based on the new systems are easily established. Authentication and signature…