Adversarial Attacks on Protein Language Models

Carbone, Ginevra; Cuturello, Francesca; Bortolussi, Luca; Cazzaniga, Alberto

doi:10.1101/2022.10.24.513465

Cited by 3 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to advancing attacks and defenses on traditional models, we also acknowledge the transformative impact of large language models in the field of recommender systems [3,40,50]. Despite their powerful generative capabilities, these models are also susceptible to various attacks [39]. Therefore, our future research will also focus on the development of attack and defense mechanisms specifically tailored to large language model-based recommendations.…”

Section: Discussionmentioning

confidence: 99%

RecAD: Towards A Unified Library for Recommender Attack and Defense

WANG,

Ye,

Wang

et al. 2023

Proceedings of the 17th ACM Conference on Recommender Systems

View full text Add to dashboard Cite

In recent years, recommender systems have become a ubiquitous part of our daily lives, while they suffer from a high risk of being attacked due to the growing commercial and social values. Despite significant research progress in recommender attack and defense, there is a lack of a widely-recognized benchmarking standard in the field, leading to unfair performance comparison and limited credibility of experiments. To address this, we propose RecAD, a unified library aiming at establishing an open benchmark for recommender attack and defense. RecAD takes an initial step to set up a unified benchmarking pipeline for reproducible research by integrating diverse datasets, standard source codes, hyper-parameter settings, running logs, attack knowledge, attack budget, and evaluation results. The benchmark is designed to be comprehensive and sustainable, covering both attack, defense, and evaluation tasks, enabling more researchers to easily follow and contribute to this promising field. RecAD will drive more solid and reproducible research on recommender systems attack and defense, reduce the redundant efforts of researchers, and ultimately increase the credibility and practical value of recommender attack and defense. The project is released at https://github.com/gusye1234/recad. CCS CONCEPTS• Information systems → Recommender systems.

show abstract

Section: Discussionmentioning

confidence: 99%

RecAD: Towards A Unified Library for Recommender Attack and Defense

WANG,

Ye,

Wang

et al. 2023

Proceedings of the 17th ACM Conference on Recommender Systems

View full text Add to dashboard Cite

show abstract

“…Such data points are particularly threatening for DNNs in the field of biomedical analysis due to concerns regarding prediction integrity and security ( Ozbulak et al 2019 ). Although such data points are first and foremost a threat in terms of security, a number of studies revealed that it is possible to leverage them for the purpose of DNN interpretability ( Pezeshkpour et al 2019 , Tao et al 2018 ), for example, to understand protein structures, which makes them relevant to our study ( Carbone et al 2022 ).…”

Section: Introductionmentioning

confidence: 99%

Mutate and observe: utilizing deep neural networks to investigate the impact of mutations on translation initiation

et al. 2023

View full text Add to dashboard Cite

Motivation The primary regulatory step for protein synthesis is translation initiation, which makes it one of the fundamental steps in the central dogma of molecular biology. In recent years, a number of approaches relying on deep neural networks (DNNs) have demonstrated superb results for predicting translation initiation sites. These state-of-the art results indicate that DNNs are indeed capable of learning complex features that are relevant to the process of translation. Unfortunately, most of those research efforts that employ DNNs only provide shallow insights into the decision-making processes of the trained models and lack highly sought-after novel biologically relevant observations. Results By improving upon the state-of-the-art DNNs and large-scale human genomic datasets in the area of translation initiation, we propose an innovative computational methodology to get neural networks to explain what was learned from data. Our methodology, which relies on in silico point mutations, reveals that DNNs trained for translation initiation site detection correctly identify well-established biological signals relevant to translation, including (1) the importance of the Kozak sequence, (2) the damaging consequences of ATG mutations in the 5’ untranslated region (UTR), (3) the detrimental effect of premature stop codons in the coding region, and (4) the relative insignificance of cytosine mutations for translation. Furthermore, we delve deeper into the Beta-globin gene and investigate various mutations that lead to the Beta thalassemia disorder. Finally, we conclude our work by laying out a number of novel observations regarding mutations and translation initiation. Availability For data, models, and code, visit github.com/utkuozbulak/mutate-and-observe Supplementary information Supplementary data are available at Bioinformatics online.

show abstract