The Defense Department’s Semantic Forensics (SemaFor) grant aims to develop cutting-edge technologies to automatically recognize, attribute, and describe modified multi-modal media assets in order to combat widespread, automated disinformation attacks. By advancing beyond traditional statistical detection methods, this grant focuses on innovative semantic technologies that can pinpoint inconsistencies in falsified media, making it more challenging for adversaries to deceive with manipulated content. SemaFor seeks to enhance media analysis by creating algorithms for semantic detection, attribution, and characterization, ultimately aiding in the identification, prevention, and comprehension of hostile disinformation efforts.
Opportunity ID: 319894
General Information
| Document Type: | Grants Notice |
| Funding Opportunity Number: | HR001119S0085 |
| Funding Opportunity Title: | Semantic Forensics (SemaFor) |
| Opportunity Category: | Discretionary |
| Opportunity Category Explanation: | – |
| Funding Instrument Type: | Grant Procurement Contract |
| Category of Funding Activity: | Science and Technology and other Research and Development |
| Category Explanation: | – |
| Expected Number of Awards: | – |
| Assistance Listings: | 12.910 — Research and Technology Development |
| Cost Sharing or Matching Requirement: | No |
| Version: | Synopsis 3 |
| Posted Date: | Aug 23, 2019 |
| Last Updated Date: | Aug 29, 2019 |
| Original Closing Date for Applications: | Nov 21, 2019 See Full Announcement for details. |
| Current Closing Date for Applications: | Nov 21, 2019 See Full Announcement for details. |
| Archive Date: | Dec 21, 2019 |
| Estimated Total Program Funding: | – |
| Award Ceiling: | – |
| Award Floor: | – |
Eligibility
| Eligible Applicants: | Others (see text field entitled “Additional Information on Eligibility” for clarification) |
| Additional Information on Eligibility: | All responsible sources capable of satisfying the Government’s needs may submit a proposal that shall be considered by DARPA. See the Eligibility Information section of the BAA for more information. |
Additional Information
| Agency Name: | DARPA – Information Innovation Office |
| Description: | The Semantic Forensics (SemaFor) program will develop technologies to automatically detect, attribute, and characterize falsified multi-modal media assets (text, audio, image, video) to defend against large-scale, automated disinformation attacks. Statistical detection techniques have been successful, but media generation and manipulation technology is advancing rapidly. Purely statistical detection methods are quickly becoming insufficient for detecting falsified media assets. Detection techniques that rely on statistical fingerprints can often be fooled with limited additional resources (algorithm development, data, or compute). However, existing automated media generation and manipulation algorithms are heavily reliant on purely data driven approaches and are prone to making semantic errors. For example, GAN-generated faces may have semantic inconsistencies such as mismatched earrings. These semantic failures provide an opportunity for defenders to gain an asymmetric advantage. A comprehensive suite of semantic inconsistency detectors would dramatically increase the burden on media falsifiers, requiring the creators of falsified media to get every semantic detail correct, while defenders only need to find one, or a very few, inconsistencies. SemaFor seeks to develop innovative semantic technologies for analyzing media. Semantic detection algorithms will determine if media is generated or manipulated. Attribution algorithms will infer if media originates from a particular organization or individual. Characterization algorithms will reason about whether media was generated or manipulated for malicious purposes. These SemaFor technologies will help identify, deter, and understand adversary disinformation campaigns. |
| Link to Additional Information: | FedBizOpps Announcement |
| Grantor Contact Information: | If you have difficulty accessing the full announcement electronically, please contact:
BAA Coordinator
SemaFor@darpa.mil Email:SemaFor@darpa.mil |
Version History
| Version | Modification Description | Updated Date |
|---|---|---|
| Team would like to update the Quad Chart requirement for submitters. | Aug 29, 2019 | |
| Team would like to update the Quad Chart requirement for submitters. | Aug 23, 2019 | |
| Aug 23, 2019 |
DISPLAYING: Synopsis 3
General Information
| Document Type: | Grants Notice |
| Funding Opportunity Number: | HR001119S0085 |
| Funding Opportunity Title: | Semantic Forensics (SemaFor) |
| Opportunity Category: | Discretionary |
| Opportunity Category Explanation: | – |
| Funding Instrument Type: | Grant Procurement Contract |
| Category of Funding Activity: | Science and Technology and other Research and Development |
| Category Explanation: | – |
| Expected Number of Awards: | – |
| Assistance Listings: | 12.910 — Research and Technology Development |
| Cost Sharing or Matching Requirement: | No |
| Version: | Synopsis 3 |
| Posted Date: | Aug 23, 2019 |
| Last Updated Date: | Aug 29, 2019 |
| Original Closing Date for Applications: | Nov 21, 2019 See Full Announcement for details. |
| Current Closing Date for Applications: | Nov 21, 2019 See Full Announcement for details. |
| Archive Date: | Dec 21, 2019 |
| Estimated Total Program Funding: | – |
| Award Ceiling: | – |
| Award Floor: | – |
Eligibility
| Eligible Applicants: | Others (see text field entitled “Additional Information on Eligibility” for clarification) |
| Additional Information on Eligibility: | All responsible sources capable of satisfying the Government’s needs may submit a proposal that shall be considered by DARPA. See the Eligibility Information section of the BAA for more information. |
Additional Information
| Agency Name: | DARPA – Information Innovation Office |
| Description: | The Semantic Forensics (SemaFor) program will develop technologies to automatically detect, attribute, and characterize falsified multi-modal media assets (text, audio, image, video) to defend against large-scale, automated disinformation attacks. Statistical detection techniques have been successful, but media generation and manipulation technology is advancing rapidly. Purely statistical detection methods are quickly becoming insufficient for detecting falsified media assets. Detection techniques that rely on statistical fingerprints can often be fooled with limited additional resources (algorithm development, data, or compute). However, existing automated media generation and manipulation algorithms are heavily reliant on purely data driven approaches and are prone to making semantic errors. For example, GAN-generated faces may have semantic inconsistencies such as mismatched earrings. These semantic failures provide an opportunity for defenders to gain an asymmetric advantage. A comprehensive suite of semantic inconsistency detectors would dramatically increase the burden on media falsifiers, requiring the creators of falsified media to get every semantic detail correct, while defenders only need to find one, or a very few, inconsistencies. SemaFor seeks to develop innovative semantic technologies for analyzing media. Semantic detection algorithms will determine if media is generated or manipulated. Attribution algorithms will infer if media originates from a particular organization or individual. Characterization algorithms will reason about whether media was generated or manipulated for malicious purposes. These SemaFor technologies will help identify, deter, and understand adversary disinformation campaigns. |
| Link to Additional Information: | FedBizOpps Announcement |
| Grantor Contact Information: | If you have difficulty accessing the full announcement electronically, please contact:
BAA Coordinator
SemaFor@darpa.mil Email:SemaFor@darpa.mil |
DISPLAYING: Synopsis 2
General Information
| Document Type: | Grants Notice |
| Funding Opportunity Number: | HR001119S0085 |
| Funding Opportunity Title: | Semantic Forensics (SemaFor) |
| Opportunity Category: | Discretionary |
| Opportunity Category Explanation: | – |
| Funding Instrument Type: | Grant Procurement Contract |
| Category of Funding Activity: | Science and Technology and other Research and Development |
| Category Explanation: | – |
| Expected Number of Awards: | – |
| Assistance Listings: | 12.910 — Research and Technology Development |
| Cost Sharing or Matching Requirement: | No |
| Version: | Synopsis 2 |
| Posted Date: | Aug 23, 2019 |
| Last Updated Date: | Aug 29, 2019 |
| Original Closing Date for Applications: | – |
| Current Closing Date for Applications: | Nov 21, 2019 See Full Announcement for details. |
| Archive Date: | Dec 21, 2019 |
| Estimated Total Program Funding: | – |
| Award Ceiling: | – |
| Award Floor: | – |
Eligibility
| Eligible Applicants: | Others (see text field entitled “Additional Information on Eligibility” for clarification) |
| Additional Information on Eligibility: | All responsible sources capable of satisfying the Government’s needs may submit a proposal that shall be considered by DARPA. See the Eligibility Information section of the BAA for more information. |
Additional Information
| Agency Name: | DARPA – Information Innovation Office |
| Description: | The Semantic Forensics (SemaFor) program will develop technologies to automatically detect, attribute, and characterize falsified multi-modal media assets (text, audio, image, video) to defend against large-scale, automated disinformation attacks. Statistical detection techniques have been successful, but media generation and manipulation technology is advancing rapidly. Purely statistical detection methods are quickly becoming insufficient for detecting falsified media assets. Detection techniques that rely on statistical fingerprints can often be fooled with limited additional resources (algorithm development, data, or compute). However, existing automated media generation and manipulation algorithms are heavily reliant on purely data driven approaches and are prone to making semantic errors. For example, GAN-generated faces may have semantic inconsistencies such as mismatched earrings. These semantic failures provide an opportunity for defenders to gain an asymmetric advantage. A comprehensive suite of semantic inconsistency detectors would dramatically increase the burden on media falsifiers, requiring the creators of falsified media to get every semantic detail correct, while defenders only need to find one, or a very few, inconsistencies. SemaFor seeks to develop innovative semantic technologies for analyzing media. Semantic detection algorithms will determine if media is generated or manipulated. Attribution algorithms will infer if media originates from a particular organization or individual. Characterization algorithms will reason about whether media was generated or manipulated for malicious purposes. These SemaFor technologies will help identify, deter, and understand adversary disinformation campaigns. |
| Link to Additional Information: | FedBizOpps Announcement |
| Grantor Contact Information: | If you have difficulty accessing the full announcement electronically, please contact:
BAA Coordinator
SemaFor@darpa.mil Email:SemaFor@darpa.mil |
DISPLAYING: Synopsis 1
General Information
| Document Type: | Grants Notice |
| Funding Opportunity Number: | HR001119S0085 |
| Funding Opportunity Title: | Semantic Forensics (SemaFor) |
| Opportunity Category: | Discretionary |
| Opportunity Category Explanation: | – |
| Funding Instrument Type: | Grant Procurement Contract |
| Category of Funding Activity: | Science and Technology and other Research and Development |
| Category Explanation: | – |
| Expected Number of Awards: | – |
| Assistance Listings: | 12.910 — Research and Technology Development |
| Cost Sharing or Matching Requirement: | No |
| Version: | Synopsis 1 |
| Posted Date: | Aug 23, 2019 |
| Last Updated Date: | Aug 23, 2019 |
| Original Closing Date for Applications: | – |
| Current Closing Date for Applications: | Nov 21, 2019 See Full Announcement for details. |
| Archive Date: | Dec 21, 2019 |
| Estimated Total Program Funding: | – |
| Award Ceiling: | – |
| Award Floor: | – |
Eligibility
| Eligible Applicants: | Others (see text field entitled “Additional Information on Eligibility” for clarification) |
| Additional Information on Eligibility: | All responsible sources capable of satisfying the Government’s needs may submit a proposal that shall be considered by DARPA. See the Eligibility Information section of the BAA for more information. |
Additional Information
| Agency Name: | DARPA – Information Innovation Office |
| Description: | The Semantic Forensics (SemaFor) program will develop technologies to automatically detect, attribute, and characterize falsified multi-modal media assets (text, audio, image, video) to defend against large-scale, automated disinformation attacks. Statistical detection techniques have been successful, but media generation and manipulation technology is advancing rapidly. Purely statistical detection methods are quickly becoming insufficient for detecting falsified media assets. Detection techniques that rely on statistical fingerprints can often be fooled with limited additional resources (algorithm development, data, or compute). However, existing automated media generation and manipulation algorithms are heavily reliant on purely data driven approaches and are prone to making semantic errors. For example, GAN-generated faces may have semantic inconsistencies such as mismatched earrings. These semantic failures provide an opportunity for defenders to gain an asymmetric advantage. A comprehensive suite of semantic inconsistency detectors would dramatically increase the burden on media falsifiers, requiring the creators of falsified media to get every semantic detail correct, while defenders only need to find one, or a very few, inconsistencies. SemaFor seeks to develop innovative semantic technologies for analyzing media. Semantic detection algorithms will determine if media is generated or manipulated. Attribution algorithms will infer if media originates from a particular organization or individual. Characterization algorithms will reason about whether media was generated or manipulated for malicious purposes. These SemaFor technologies will help identify, deter, and understand adversary disinformation campaigns. |
| Link to Additional Information: | FedBizOpps Announcement |
| Grantor Contact Information: | If you have difficulty accessing the full announcement electronically, please contact:
BAA Coordinator
HR001119S0085@darpa.mil Email:HR001119S0085@darpa.mil |
Related Documents
Folder 319894 Full Announcement-HR001119S0085 -> SemaFor_BAA_Attachment_Proposal_Summary_Chart_Template.pdf
Folder 319894 Full Announcement-HR001119S0085 -> SemaFor_BAA_proposal_LoE_table_template_SkillSets.pdf
Folder 319894 Full Announcement-HR001119S0085 -> SemaFor_CUI_Guide_20190702_Approved.pdf
Folder 319894 Full Announcement-HR001119S0085 -> HR001119S0085.pdf
Folder 319894 Revised Full Announcement-HR001119S0085-Amendment-01 -> BAA-SemaForProposerOverviewChart-v2.pdf
Folder 319894 Revised Full Announcement-HR001119S0085-Amendment-01 -> HR001119S0085-Amendment-01.pdf
Packages
| Agency Contact Information: | BAA Coordinator SemaFor@darpa.mil Email: SemaFor@darpa.mil |
| Who Can Apply: | Organization Applicants |
| Assistance Listing Number | Competition ID | Competition Title | Opportunity Package ID | Opening Date | Closing Date | Actions |
|---|---|---|---|---|---|---|
| 12.910 | PKG00254198 | Aug 23, 2019 | Nov 21, 2019 | View |
Package 1
Mandatory forms
319894 RR_SF424_2_0-2.0.pdf
319894 RR_KeyPersonExpanded_2_0-2.0.pdf
319894 RR_PersonalData_1_2-1.2.pdf
Optional forms
319894 AttachmentForm_1_2-1.2.pdf
319894 RR_OtherProjectInfo_1_4-1.4.pdf
319894 PerformanceSite_2_0-2.0.pdf
319894 SFLLL_1_2-1.2.pdf
319894 Project_Abstract_1_2-1.2.pdf
319894 RR_Budget10_1_4-1.4.pdf
319894 RR_SubawardBudget10_30_1_4-1.4.pdf
Share This Post, Choose Your Platform!
About the Author: osnqt
