{"id":{"repo_id":"ets-quebec","oai_identifier":"oai:espace.etsmtl.ca:4120"},"canonical_url":"https://search.ndltd.org/etd/ets-quebec/oai:espace.etsmtl.ca:4120","repository":{"repo_id":"ets-quebec","name":"ETS (Quebec)","base_url":"https://espace.etsmtl.ca/cgi/oai2"},"display":{"title":"ExploitGen: automated smart contract vulnerability verification via taxonomy specialized multi-agent detection and proof-of-concept exploit generation","abstract":"Smart contracts underpin decentralized finance (DeFi), where software vulnerabilities cause irreversible financial losses. Existing automated auditing approaches face a detection–verification gap: static analyzers and single-agent large language model (LLM) systems exhibit low recall, whereas unverified multi-agent architectures achieve high recall at the cost of prohibitive false-positive rates that overwhelm human auditors and negate the efficiency benefits of automation. This thesis presents ExploitGen, a LangGraph orchestrated multi-agent pipeline that closes this gap by coupling taxonomy-specialized detection with executable verification. Eight detection agents, each scoped to a single OpenSCV category, first maximize recall. Each candidate then passes through a verification sequence: static graph extraction, falsification-first validation, semantic characterization, Structured Chain-of-Thought (SCoT) attack planning, proof-of-concept (PoC) synthesis, and counterfactual confirmation. A vulnerability is confirmed only when its generated Foundry PoC passes on the vulnerable contract and fails on a signature-preserving patched counterpart, establishing exploitability causally rather than by syntactic resemblance. Evaluated on the SB Curated benchmark against 139 ground truth vulnerabilities, ExploitGen verifies 86 counterfactually confirmed exploits at a confirmation yield of 0.741 and an F1-score of 0.675. Against a single-attempt configuration of the same pipeline, unconfirmed candidates fall by 23.1% while confirmed exploits rise from 73 to 86. Against the detection-only paradigm, which uses unscoped parallel detection, unconfirmed findings fall from 342 to 30. A controlled ablation shows that SCoT planning improves reentrancy F1 by 0.200 but degrades access-control performance, establishing that component selection must be adapted to the vulnerability class. The augmented dataset of 139 patched contracts is released to support reproducibility.","abstract_html":"Smart contracts underpin decentralized finance (DeFi), where software vulnerabilities cause irreversible financial losses. Existing automated auditing approaches face a detection–verification gap: static analyzers and single-agent large language model (LLM) systems exhibit low recall, whereas unverified multi-agent architectures achieve high recall at the cost of prohibitive false-positive rates that overwhelm human auditors and negate the efficiency benefits of automation. This thesis presents ExploitGen, a LangGraph orchestrated multi-agent pipeline that closes this gap by coupling taxonomy-specialized detection with executable verification. Eight detection agents, each scoped to a single OpenSCV category, first maximize recall. Each candidate then passes through a verification sequence: static graph extraction, falsification-first validation, semantic characterization, Structured Chain-of-Thought (SCoT) attack planning, proof-of-concept (PoC) synthesis, and counterfactual confirmation. A vulnerability is confirmed only when its generated Foundry PoC passes on the vulnerable contract and fails on a signature-preserving patched counterpart, establishing exploitability causally rather than by syntactic resemblance. Evaluated on the SB Curated benchmark against 139 ground truth vulnerabilities, ExploitGen verifies 86 counterfactually confirmed exploits at a confirmation yield of 0.741 and an F1-score of 0.675. Against a single-attempt configuration of the same pipeline, unconfirmed candidates fall by 23.1% while confirmed exploits rise from 73 to 86. Against the detection-only paradigm, which uses unscoped parallel detection, unconfirmed findings fall from 342 to 30. A controlled ablation shows that SCoT planning improves reentrancy F1 by 0.200 but degrades access-control performance, establishing that component selection must be adapted to the vulnerability class. The augmented dataset of 139 patched contracts is released to support reproducibility.","abstract_has_math":false,"creators":["Aminnezhad, Aysheh"],"institution":"École de technologie supérieure","degree_name":"Mémoire de maîtrise électronique","degree_level":"masters","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026-09-07","date_published":"2026-09-07","updated_at":"2026-11-18T22:11:27Z","subjects":["contrats intelligents, détection de vulnérabilités, systèmes multi-agents, vérification automatisée, sécurité blockchain"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["INSERT-YOUR-LIBRARY-ID-HERE4120"],"render_values":[{"text":"INSERT-YOUR-LIBRARY-ID-HERE4120","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null,"record_url":null,"record_label":null,"record_kind":null,"record_source":null,"download_url":"https://espace.etsmtl.ca/id/eprint/4120/1/AMINNEZHAD_Aysheh.pdf","download_label":"Download PDF","download_source":"dc:identifier","access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://espace.etsmtl.ca/cgi/oai2?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Aespace.etsmtl.ca%3A4120","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Aminnezhad, Aysheh"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026-09-07"]},{"key":"dc:publisher","label":"Institution","values":["École de technologie supérieure"]},{"key":"dc:type","label":"Dc Type","values":["Electronic Thesis or Dissertation"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Mémoire de maîtrise électronique"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["École de technologie supérieure"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["contrats intelligents, détection de vulnérabilités, systèmes multi-agents, vérification automatisée, sécurité blockchain"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["INSERT-YOUR-LIBRARY-ID-HERE4120","https://espace.etsmtl.ca/id/eprint/4120/1/AMINNEZHAD_Aysheh.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Smart contracts underpin decentralized finance (DeFi), where software vulnerabilities cause irreversible financial losses. Existing automated auditing approaches face a detection–verification gap: static analyzers and single-agent large language model (LLM) systems exhibit low recall, whereas unverified multi-agent architectures achieve high recall at the cost of prohibitive false-positive rates that overwhelm human auditors and negate the efficiency benefits of automation. This thesis presents ExploitGen, a LangGraph orchestrated multi-agent pipeline that closes this gap by coupling taxonomy-specialized detection with executable verification. Eight detection agents, each scoped to a single OpenSCV category, first maximize recall. Each candidate then passes through a verification sequence: static graph extraction, falsification-first validation, semantic characterization, Structured Chain-of-Thought (SCoT) attack planning, proof-of-concept (PoC) synthesis, and counterfactual confirmation. A vulnerability is confirmed only when its generated Foundry PoC passes on the vulnerable contract and fails on a signature-preserving patched counterpart, establishing exploitability causally rather than by syntactic resemblance. Evaluated on the SB Curated benchmark against 139 ground truth vulnerabilities, ExploitGen verifies 86 counterfactually confirmed exploits at a confirmation yield of 0.741 and an F1-score of 0.675. Against a single-attempt configuration of the same pipeline, unconfirmed candidates fall by 23.1% while confirmed exploits rise from 73 to 86. Against the detection-only paradigm, which uses unscoped parallel detection, unconfirmed findings fall from 342 to 30. A controlled ablation shows that SCoT planning improves reentrancy F1 by 0.200 but degrades access-control performance, establishing that component selection must be adapted to the vulnerability class. The augmented dataset of 139 patched contracts is released to support reproducibility."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["ExploitGen: automated smart contract vulnerability verification via taxonomy specialized multi-agent detection and proof-of-concept exploit generation"]}]}],"canonical_facts":{"dc:creator":["Aminnezhad, Aysheh"],"dc:date":["2026-09-07"],"dc:description":["Smart contracts underpin decentralized finance (DeFi), where software vulnerabilities cause irreversible financial losses. Existing automated auditing approaches face a detection–verification gap: static analyzers and single-agent large language model (LLM) systems exhibit low recall, whereas unverified multi-agent architectures achieve high recall at the cost of prohibitive false-positive rates that overwhelm human auditors and negate the efficiency benefits of automation. This thesis presents ExploitGen, a LangGraph orchestrated multi-agent pipeline that closes this gap by coupling taxonomy-specialized detection with executable verification. Eight detection agents, each scoped to a single OpenSCV category, first maximize recall. Each candidate then passes through a verification sequence: static graph extraction, falsification-first validation, semantic characterization, Structured Chain-of-Thought (SCoT) attack planning, proof-of-concept (PoC) synthesis, and counterfactual confirmation. A vulnerability is confirmed only when its generated Foundry PoC passes on the vulnerable contract and fails on a signature-preserving patched counterpart, establishing exploitability causally rather than by syntactic resemblance. Evaluated on the SB Curated benchmark against 139 ground truth vulnerabilities, ExploitGen verifies 86 counterfactually confirmed exploits at a confirmation yield of 0.741 and an F1-score of 0.675. Against a single-attempt configuration of the same pipeline, unconfirmed candidates fall by 23.1% while confirmed exploits rise from 73 to 86. Against the detection-only paradigm, which uses unscoped parallel detection, unconfirmed findings fall from 342 to 30. A controlled ablation shows that SCoT planning improves reentrancy F1 by 0.200 but degrades access-control performance, establishing that component selection must be adapted to the vulnerability class. The augmented dataset of 139 patched contracts is released to support reproducibility."],"dc:format":["application/pdf"],"dc:identifier":["INSERT-YOUR-LIBRARY-ID-HERE4120","https://espace.etsmtl.ca/id/eprint/4120/1/AMINNEZHAD_Aysheh.pdf"],"dc:language":["en"],"dc:publisher":["École de technologie supérieure"],"dc:subject":["contrats intelligents, détection de vulnérabilités, systèmes multi-agents, vérification automatisée, sécurité blockchain"],"dc:title":["ExploitGen: automated smart contract vulnerability verification via taxonomy specialized multi-agent detection and proof-of-concept exploit generation"],"dc:type":["Electronic Thesis or Dissertation"],"thesis:degree_level":["masters"],"thesis:degree_name":["Mémoire de maîtrise électronique"],"thesis:institution_name":["École de technologie supérieure"]},"updated_at":"2026-11-18T22:11:27Z"}