Related papers: Brute force searching, the typical set and Guesswo…
The success of neural networks on a diverse set of NLP tasks has led researchers to question how much these networks actually ``know'' about natural language. Probes are a natural way of assessing this. When probing, a researcher chooses a…
Language models are prone to memorizing their training data, making them vulnerable to extraction attacks. While existing research often examines isolated setups, such as a single model or a fixed prompt, real-world adversaries have a…
Word sense disambiguation is a well-known source of translation errors in NMT. We posit that some of the incorrect disambiguation choices are due to models' over-reliance on dataset artifacts found in training data, specifically superficial…
In multiple domains such as malware detection, automated driving systems, or fraud detection, classification algorithms are susceptible to being attacked by malicious agents willing to perturb the value of instance covariates to pursue…
We introduce a symmetrization technique which can be used as an extra step in some continuous-variable quantum key distribution protocols. By randomizing the data in phase space, one can dramatically simplify the security analysis of the…
The problem of guessing a random string is revisited. A close relation between guessing and compression is first established. Then it is shown that if the sequence of distributions of the information spectrum satisfies the large deviation…
Recently, we can observe a significant increase of the phishing attacks in the Internet. In a typical phishing attack, the attacker sets up a malicious website that looks similar to the legitimate website in order to obtain the end-users'…
The security of passwords depends on a thorough understanding of the strategies used by attackers. Unfortunately, real-world adversaries use pragmatic guessing tactics like dictionary attacks, which are difficult to simulate in password…
Cybersecurity attacks are growing both in frequency and sophistication over the years. This increasing sophistication and complexity call for more advancement and continuous innovation in defensive strategies. Traditional methods of…
The problem of guessing subject to distortion is considered, and the performance of randomized guessing strategies is investigated. A one-shot achievability bound on the guessing moment (i.e., moment of the number of required queries) is…
Usually, probabilistic automata and probabilistic grammars have crisp symbols as inputs, which can be viewed as the formal models of computing with values. In this paper, we first introduce probabilistic automata and probabilistic grammars…
Normative decision theory proves inadequate for modeling human responses to the social-engineering campaigns of Advanced Persistent Threat (APT) attacks. Behavioral decision theory fares better, but still falls short of capturing…
Truth discovery is a general name for a broad range of statistical methods aimed to extract the correct answers to questions, based on multiple answers coming from noisy sources. For example, workers in a crowdsourcing platform. In this…
The power law is useful in describing count phenomena such as network degrees and word frequencies. With a single parameter, it captures the main feature that the frequencies are linear on the log-log scale. Nevertheless, there have been…
This work examines an imbalance in artificial intelligence (AI) security research: the field tends to produce more work on attacking AI systems than on defending them. Drawing on related academic papers, we find biased attack-to-defense…
In adaptive data analysis, a mechanism gets $n$ i.i.d. samples from an unknown distribution $D$, and is required to provide accurate estimations to a sequence of adaptively chosen statistical queries with respect to $D$. Hardt and Ullman…
We introduce a graceful approach to probabilistic inference called bounded conditioning. Bounded conditioning monotonically refines the bounds on posterior probabilities in a belief network with computation, and converges on final…
Wake-up word detection models are widely used in real life, but suffer from severe performance degradation when encountering adversarial samples. In this paper we discuss the concept of confusing words in adversarial samples. Confusing…
Given that distributed systems face adversarial behaviors such as eavesdropping and cyberattacks, how to ensure the evidence fusion result is credible becomes a must-be-addressed topic. Different from traditional research that assumes nodes…
In the past two decades we have seen the popularity of neural networks increase in conjunction with their classification accuracy. Parallel to this, we have also witnessed how fragile the very same prediction models are: tiny perturbations…