To combat the rapid spread of misinformation on social networks, automated misinformation detection systems based on deep neural networks (DNNs) have been developed. However, these tools are often proprietary and lack transparency, which limits their usefulness. Furthermore, privacy concerns limit data sharing by data owners as well as by data-driven misinformation-detection services. Although data encryption techniques can help address privacy concerns in DNN inference, there is a challenge to the seamless integration of these techniques due to the encryption errors induced by cascaded encrypted operations, as well as a mismatch between the tools used for DNNs and cryptography. In this paper, we make two-fold contributions. First, we study the noise bounds of homomorphic encryption (HE) operations as error propagation in DNN layers and derive two properties that, if satisfied by the layer, will considerably reduce the output error. We identify that$L_{2}$regularization and sigmoid activation satisfy these properties and validate our hypothesis, for instance, replacing ReLU with sigmoid reduced the output error by$10^{6}\times$(best case) to$10\times$(worst case). Second, we extend the Python encryption library TenSeal by enabling the automatic conversion of a TensorFlow DNN into an encryption-compatible DNN with a few lines of code. These contributions are significant as encryption-friendly DL architectures are sorely needed to close the gap between DL-in-research and DL-in-practice.

Deep Learning (DL) algorithms have shown wonders in many Natural Language Processing (NLP) tasks such as language-to-language translation, spam filtering, fake-news detection, and comprehension understanding. However, research has shown that the adversarial vulnerabilities of deep learning networks manifest themselves when DL is used for NLP tasks. Most mitigation techniques proposed to date are supervised—relying on adversarial retraining to improve the robustness—which is impractical. This work introduces a novel, unsupervised detection methodology for detecting adversarial inputs to NLP classifiers. In summary, we note that minimally perturbing an input to change a model’s output—a major strength of adversarial attacks—is a weakness that leaves unique statistical marks reflected in the cumulative contribution scores of the input. Particularly, we show that the cumulative contribution score, called CF-score, of adversarial inputs is generally greater than that of the clean inputs. We thus propose Con-Detect—a Contribution based Detection method—for detecting adversarial attacks against NLP classifiers. Con-Detect can be deployed with any classifier without having to retrain it. We experiment with multiple attackers—Text-bugger, Text-fooler, PWWS—on several architectures—MLP, CNN, LSTM, Hybrid CNN-RNN, BERT—trained for different classification tasks—IMDB sentiment classification, fake-news classification, AG news topic classification—under different threat models—Con-Detect-blind attacks, Con-Detect-aware attacks, and Con-Detect-adaptive attacks—and show that Con-Detect can reduce the attack success rate (ASR) of different attacks from 100% to as low as 0% for the best cases and ≈70% for the worst case. Even in the worst case, we note a 100% increase in the required number of queries and a 50% increase in the number of words perturbed, suggesting that Con-Detect is hard to evade.

Testing systems-on-a-chip involves applying huge amounts of test data, which is stored in the tester memory and then transferred to the circuit under test during test application. Therefore, practical techniques, such as test compression and compaction, are required to reduce the amount of test data in order to reduce both the total testing time and the memory requirements for the tester. Test-set relaxation can improve the efficiency of both test compression and test compaction. In addition, the relaxation process can identify self-initializing test sequences for synchronous sequential circuits. In this paper, we propose an efficient test-relaxation technique for synchronous sequential circuits that maximizes the number of unspecified bits while maintaining the same fault coverage as the original test set.

Testing systems-on-a-chip (SOC) involves applying huge amounts of test data, which is stored in the tester memory and then transferred to the circuit under test (CUT) during test application. Therefore, practical techniques, such as test compression and compaction, are required to reduce the amount of test data in order to reduce both the total testing time and the memory requirements for the tester Relaxing test sequences can improve the efficiency of both test compression and test compaction. In addition, the relaxation process can identify self-initializing test sequences for synchronous sequential circuits. In this paper we propose an efficient test relaxation technique for synchronous sequential circuits that maximizes the number of unspecified bits while maintaining the same fault coverage as the original test set.