{"paper_id":"2406.10719","title":"Trading Devil: Robust backdoor attack via Stochastic investment models and Bayesian approach","authors":["Orson Mengara"],"paper_date":"2024-06-15","paper_type":"methodological","paper_url":"https://arxiv.org/pdf/2406.10719v5","page_url":"https://thequant.space/flowcharts/trading-devil-robust-backdoor-attack-via-stochastic-investm/","scores":{"empirical_rigor":3,"math_complexity":8.5,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes a robust clean‑label backdoor attack called MarketBack that leverages stochastic investment models (Vasicek, Hull‑White, Longstaff‑Schwartz) and a Bayesian diffusion approach.","quote":"In this paper, we present a paradigm for creating a robust clean-label backdoor attack [15] (algorithm 5), incorporating the effects of drift.","summary":"With the growing use of voice-activated systems and speech recognition technologies, the danger of backdoor attacks on audio data has grown significantly. This research looks at a specific type of attack, known as a Stochastic investment-based backdoor attack (MarketBack), in which adversaries…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The attacker can outsource model training to untrustworthy third parties.","type":"execution","stated":"explicit","quote":"…er outsources model training to third parties), the attacker can insert a hidden behavior (called a backdoor) into the model…"},{"assumption":"Poisoning rate is low (less than 1% of training data).","type":"data","stated":"explicit","quote":"Experimental results demonstrated that MarketBack is feasible to achieve an average attack success rate close to 100% in seven victim models when poisoning less than 1% of the training data."},{"assumption":"Backdoor triggers are imperceptible to human listeners.","type":"other","stated":"explicit","quote":"These attacks are not always stealthy, because they often rely on specific acoustic features that can be easily detected by the human ear."},{"assumption":"The victim models are pre‑trained transformer speech‑recognition models from Hugging Face.","type":"model","stated":"explicit","quote":"Table I presents the different results obtained using our backdoor attack approach (MarketBack) on pre‑trained models (transformers"},{"assumption":"The backdoor target label is the class ‘3’.","type":"other","stated":"explicit","quote":"ASR, in turn, measures the success of the backdoor attack, i.e., in causing the model to misclassify poisoned test examples. It indicates the percentage of poisoned examples that are classified as the target label (‘3’ in our case)…"}]},"datasets":{"status":"available","items":[{"name":"GTZAN musical compositions","provider":null,"kind":"benchmark","access":"public","period":null,"universe":"1000 musical compositions in 10 distinct genres","quote":"2 1000 musical compositions in 10 distinct genres; GTZAN."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"unclear"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"unclear","findings":[{"finding":"MarketBack achieves 100% attack success rate on all tested Hugging Face transformer models while maintaining high benign accuracy.","kind":"performance","quote":"hubert-large-ls960-ft 97.63% 100% ... whisper-large-v3 (OpenAI) 93.06% 100%"},{"finding":"The attack succeeds with less than 1% poisoning of the training data.","kind":"performance","quote":"Experimental results demonstrated that MarketBack is feasible to achieve an average attack success rate close to 100% in seven victim models when poisoning less than 1% of the training data."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":8,"citations":{"cited_by_in_corpus":1,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":1},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T18:07:34Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}