More Like this

1. Generating Literal and Implied Subquestions to Fact-check Complex Claims

   Chen, Jifan; Sriram, Aniruddh; Choi, Eunsol; Durrett, Greg (January 2022, Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP))

   Verifying political claims is a challenging task, as politicians can use various tactics to subtly misrepresent the facts for their agenda. Existing automatic fact-checking systems fall short here, and their predictions like "half-true" are not very useful in isolation, since it is unclear which parts of a claim are true or false. In this work, we focus on decomposing a complex claim into a comprehensive set of yes-no subquestions whose answers influence the veracity of the claim. We present CLAIMDECOMP, a dataset of decompositions for over 1000 claims. Given a claim and its verification paragraph written by fact-checkers, our trained annotators write subquestions covering both explicit propositions of the original claim and its implicit facets, such as additional political context that changes our view of the claim's veracity. We study whether state-of-the-art pre-trained models can learn to generate such subquestions. Our experiments show that these models generate reasonable questions, but predicting implied subquestions based only on the claim (without consulting other evidence) remains challenging. Nevertheless, we show that predicted subquestions can help identify relevant evidence to fact-check the full claim and derive the veracity through their answers, suggesting that claim decomposition can be a useful piece of a fact-checking pipeline. 

   more » « less
2. Claim Verification under Positive Unlabeled Learning

   Fan Yang, Eduard Dragut (January 2020, Proceedings of the International Conference on Advances in Social Network Analysis and Mining)

   null (Ed.)

   We extend evidence-aware claim verification to the context of positive-unlabeled (PU) learning. Existing works assume the truth and the falsity of the claims are known for training and form the task as a supervised learning problem. However, this assumption underestimates the difficulty of collecting false claims; we argue that claim verification is more challenging in the absence of negative labels. We consider a more practical setting, where only a comparatively small number of true claims are labeled and more claims remain unlabeled. Thus, we formulate the claim verification task as a PU learning problem. We decouple learning representation of claim-evidence pair from PU learning and adopt a pre-trained universal language model to encode claim-evidence pairs. We further propose to use the generative adversarial network (GAN) to capture the latent alignment between encoded claim-evidence pair and the truthfulness. We leverage the verification as part of the GAN by extending previous GAN based PU learning. We show that the proposed model achieves the best performance with a small amount of labeled data and is robust to the truthfulness prior estimation. We conduct a thorough analysis of the model selection. The proposed approach performs the best under two practical scenarios: (i) the unlabeled data is more than the labeled data; (ii) and the unlabeled positive data is more than the unlabeled negative data. 

   more » « less
3. CheckDP: An Automated and Integrated Approach for Proving Differential Privacy or Finding Precise Counterexamples

   https://doi.org/10.1145/3372297.3417282  

   Wang, Yuxin; Ding, Zeyu; Kifer, Daniel; Zhang, Danfeng (October 2020, CCS '20: Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security)

   null (Ed.)

   We propose CheckDP, an automated and integrated approach for proving or disproving claims that a mechanism is differentially private. CheckDP can find counterexamples for mechanisms with subtle bugs for which prior counterexample generators have failed. Furthermore, it was able to automatically generate proofs for correct mechanisms for which no formal verification was reported before. CheckDP is built on static program analysis, allowing it to be more efficient and precise in catching infrequent events than sampling based counterexample generators (which run mechanisms hundreds of thousands of times to estimate their output distribution). Moreover, its sound approach also allows automatic verification of correct mechanisms. When evaluated on standard benchmarks and newer privacy mechanisms, CheckDP generates proofs (for correct mechanisms) and counterexamples (for incorrect mechanisms) within 70 seconds without any false positives or false negatives. 

   more » « less
4. Generation of Low Distortion Adversarial Attacks via Convex Programming

   https://doi.org/10.1109/ICDM.2019.00195  

   Zhang, T; Liu, S; Wang, Y; Fardad, M (January 2019, IEEE International Conference on Data Mining)

   null (Ed.)

   As deep neural networks (DNNs) achieve extraordi- nary performance in a wide range of tasks, testing their robust- ness under adversarial attacks becomes paramount. Adversarial attacks, also known as adversarial examples, are used to measure the robustness of DNNs and are generated by incorporating imperceptible perturbations into the input data with the intention of altering a DNN’s classification. In prior work in this area, most of the proposed optimization based methods employ gradient descent to find adversarial examples. In this paper, we present an innovative method which generates adversarial examples via convex programming. Our experiment results demonstrate that we can generate adversarial examples with lower distortion and higher transferability than the C&W attack, which is the current state-of-the-art adversarial attack method for DNNs. We achieve 100% attack success rate on both the original undefended models and the adversarially-trained models. Our distortions of the L∞ attack are respectively 31% and 18% lower than the C&W attack for the best case and average case on the CIFAR-10 data set. 

   more » « less
5. Detecting Adversarial Audio via Activation Quantization Error

   https://doi.org/10.1109/IJCNN48605.2020.9206986  

   Liu, Heng; Ditzler, Gregory (July 2020, International Joint Conference on Neural Networks (IJCNN))

   The robustness and vulnerability of Deep Neural Networks (DNN) are quickly becoming a critical area of interest since these models are in widespread use across real-world applications (i.e., image and audio analysis, recommendation system, natural language analysis, etc.). A DNN's vulnerability is exploited by an adversary to generate data to attack the model; however, the majority of adversarial data generators have focused on image domains with far fewer work on audio domains. More recently, audio analysis models were shown to be vulnerable to adversarial audio examples (e.g., speech command classification, automatic speech recognition, etc.). Thus, one urgent open problem is to detect adversarial audio reliably. In this contribution, we incorporate a separate and yet related DNN technique to detect adversarial audio, namely model quantization. Then we propose an algorithm to detect adversarial audio by using a DNN's quantization error. Specifically, we demonstrate that adversarial audio typically exhibits a larger activation quantization error than benign audio. The quantization error is measured using character error rates. We use the difference in errors to discriminate adversarial audio. Experiments with three the-state-of-the-art audio attack algorithms against the DeepSpeech model show our detection algorithm achieved high accuracy on the Mozilla dataset. 

   more » « less