Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 8 of 8 for “"adversarial noise"”.
-
Using adversarial noise for privacy protection: an evaluation of hybrid attacks across application targets
Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-05-01
-
Multishot Capacity of Adversarial Networks
Adversarial network coding studies the transmission of data over networks affected by adversarial noise. In this realm, the noise is modeled by an omniscient adversary who is restricted to corrupting a proper subset of the network edges. In 2018, Ravagnani and Kschischang established a …
-
Cryptographic error correction
… correction in which the source of errors is adversarial, but limited to feasible computation. In this model, we construct appealingly simple, general, and efficient cryptographic coding schemes which can recover from much larger error rates than schemes for classical models of adversarial …
-
Distributed computation and inference
… distributed computations in the presence of adversarial noise. This work falls into the framework of interactive coding, which is an extension of error correcting codes to interactive settings commonly found in theoretical computer science. On the inference side, we model social and …
-
Fundamental Limits of Learning for Generalizability, Data Resilience, and Resource Efficiency
… 3), supervised learning with arbitrary or adversarial noise (Chapter 4); partial-feedback in standard contextual bandits (Chapter 5) and, as a first step towards more complex reinforcement learning settings, contextual bandits with non-stationary or adversarial rewards (Chapter 6). We …
-
Intractability Results for some Computational Problems
… to learning parities with random classification noise, commonly referred to as the noisy parity problem. Together with the parity learning algorithm of Blum et al, this gives the first nontrivial algorithm for agnostic learning of parities. We use similar techniques to reduce learning of two …
-
Balanced allocations under incomplete information: New settings and techniques
… - We analyse the Two-Choice process with random, adversarial and delay noise, proving tight bounds for various settings. In the adversarial setting, the adversary can decide in which of the two sampled bins the ball is allocated to, only when the two loads differ by at most 𝑔. The analysis of this …
-
Active and Semi-Supervised Learning for Speech Recognition
… the novel algorithm cosine-distance virtual adversarial training (CD-VAT) was developed. Whilst not directed at speech recognition, this technique was inspired by initial work towards using consistency-regularisation for speech recognition. CD-VAT allows for semi-supervised training of …