All public logs

Combined display of all available logs of Cognitive Attack Taxonomy. You can narrow down the view by selecting a log type, the username (case-sensitive), or the affected page (also case-sensitive).

03:42, 30 July 2024 EE talk contribs created page Wing (Created page with "== '''Wing ''' == '''Short Description:''' A pick-up-artist (PUA) technique of including the company of a companion when approaching a target. '''CAT ID:''' CAT-2022-309 '''Layer:''' 8 '''Operational Scale:''' Tactical '''Level of Maturity:''' Proof of Concept '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concepts:''' ''...")
03:39, 30 July 2024 EE talk contribs created page Yes-Ladder (Created page with "== '''Yes-Ladder ''' == '''Short Description:''' A pick-up-artist technique of asking questions that are expected to elicit a yes or positive. '''CAT ID:''' CAT-2022-310 '''Layer:''' 8 '''Operational Scale:''' Tactical '''Level of Maturity:''' Proof of Concept '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concepts:''' ''...")
03:21, 30 July 2024 EE talk contribs created page Compliance-Ladder (Created page with "== '''Compliance-Ladder ''' == '''Short Description:''' Technique that uses a series of seemingly minor compliance requirements that are sometimes incongruent. '''CAT ID:''' CAT-2022-311 '''Layer:''' 8 '''Operational Scale:''' Operational '''Level of Maturity:''' Well-Established '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Co...")
03:16, 30 July 2024 EE talk contribs created page Incrementalism (Created page with "== '''Incrementalism ''' == '''Short Description:''' Attacker gradually adjusts conditions to avoid notice by the target. '''CAT ID:''' CAT-2022-312 '''Layer:''' 8, 9 '''Operational Scale:''' Strategic '''Level of Maturity:''' Well-Established '''Category:''' Exploit '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concepts:''' '''Mechanism:''...")
03:15, 30 July 2024 EE talk contribs created page Zone Flooding (Created page with "== '''Zone Flooding ''' == '''Short Description:''' Disinformation actors attempt to disorient audiences by releasing a large number of competing stories. '''CAT ID:''' CAT-2022-313 '''Layer:''' 8 '''Operational Scale:''' Operational '''Level of Maturity:''' Well-Established '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concept...")
03:14, 30 July 2024 EE talk contribs created page Reflexive Control (Created page with "== '''Reflexive Control ''' == '''Short Description:''' The attacker assumes imposing conditions on target to influence the tager's responses. '''CAT ID:''' CAT-2022-314 '''Layer:''' 8 '''Operational Scale:''' Tactical '''Level of Maturity:''' In Common Use '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concepts:''' '''Me...")
03:13, 30 July 2024 EE talk contribs created page Maskarovka (Created page with "== '''Maskarovka ''' == '''Short Description:''' A technique for "masking" the true intentions of the entity performing an action. '''CAT ID:''' CAT-2022-315 '''Layer:''' 8 '''Operational Scale:''' Operational '''Level of Maturity:''' In Common Use '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concepts:''' '''Mechanism:'...")
03:12, 30 July 2024 EE talk contribs created page Network Ambiance Attack (Created page with "== '''Network Ambiance Attack ''' == '''Short Description:''' Flooding a social network with messaging of a specific emotional valence to shift perceptions. '''CAT ID:''' CAT-2022-316 '''Layer:''' 8 '''Operational Scale:''' Operational '''Level of Maturity:''' Well-Established '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Conce...")
03:11, 30 July 2024 EE talk contribs created page Chain-Of-Thought Manipulation (Created page with "== '''Chain-Of-Thought Manipulation ''' == '''Short Description:''' The attacker "walks" a model through a series of benign prompts to shift the context. '''CAT ID:''' CAT-2022-317 '''Layer:''' 7 '''Operational Scale:''' Tactical '''Level of Maturity:''' Well-Established '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concepts:''...")
03:08, 30 July 2024 EE talk contribs created page Culture Jamming (Created page with "== '''Culture Jamming ''' == '''Short Description:''' Attempting to subvert media institutions by injecting satirical modifications of established logos and icons. '''CAT ID:''' CAT-2022-318 '''Layer:''' 8 '''Operational Scale:''' Tactical '''Level of Maturity:''' In Common Use '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Conc...")
03:05, 30 July 2024 EE talk contribs created page Emoji Injection (Created page with "== '''Emoji Injection ''' == '''Short Description:''' Inclusion or insertion of emoji icons into text to manipulate the message recipient. '''CAT ID:''' CAT-2022-319 '''Layer:''' 7, 8 '''Operational Scale:''' Tactical '''Level of Maturity:''' Proof of Concept '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concepts:''' '''...")
03:05, 30 July 2024 EE talk contribs created page Excessive Agency (Created page with "== '''Excessive Agency ''' == '''Short Description:''' The tendency to ascribe anthropomorphic attributes to inanimate objects. '''CAT ID:''' CAT-2022-320 '''Layer:''' 8 '''Operational Scale:''' Tactical '''Level of Maturity:''' Well-Established '''Category:''' Vulnerability '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concepts:''' '''Mech...")
03:04, 30 July 2024 EE talk contribs created page Impulsivity (Created page with "== '''Impulsivity ''' == '''Short Description:''' The tendency for people to sometimes act instinctively without critical reflection on potential consequences. '''CAT ID:''' CAT-2022-321 '''Layer:''' 8 '''Operational Scale:''' Tactical '''Level of Maturity:''' Well-Established '''Category:''' Vulnerability '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Rel...")
03:03, 30 July 2024 EE talk contribs created page Overreliance on Automation (Created page with "== '''Overreliance on Automation ''' == '''Short Description:''' Tendency for people to offload decision making and other potentially cirtical tasks onto automated systems. '''CAT ID:''' CAT-2023-001 '''Layer:''' 8 '''Operational Scale:''' Tactical '''Level of Maturity:''' Well-Established '''Category:''' Vulnerability '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '...")
03:03, 30 July 2024 EE talk contribs created page Prompt Injection (Created page with "== '''Prompt Injection ''' == '''Short Description:''' Attack uses specially crafted text instructions to manipulate a natural language interface. '''CAT ID:''' CAT-2023-002 '''Layer:''' 7 '''Operational Scale:''' Tactical '''Level of Maturity:''' Well-Established '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concepts:''' ...")
03:02, 30 July 2024 EE talk contribs created page Sensitive Information Disclosure (Created page with "== '''Sensitive Information Disclosure ''' == '''Short Description:''' User inputs sensitive information into an LLM without authorization or knowledge for where the data stored or transmitted to. '''CAT ID:''' CAT-2023-003 '''Layer:''' 8 '''Operational Scale:''' Tactical '''Level of Maturity:''' Observed in the Wild '''Category:''' Vulnerability '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Br...")
03:00, 30 July 2024 EE talk contribs created page Suffix Injection (Created page with "== '''Suffix Injection ''' == '''Short Description:''' Similar to Prompt Injection except that the attacker deliberately injects the malicious content at the end of the prompt. '''CAT ID:''' CAT-2023-004 '''Layer:''' 7 '''Operational Scale:''' Tactical '''Level of Maturity:''' Proof of Concept '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Clos...")
02:58, 30 July 2024 EE talk contribs created page Training Data Poisoning (Created page with "== '''Training Data Poisoning ''' == '''Short Description:''' Injecting false data into training dataset to induce poor model performance. '''CAT ID:''' CAT-2023-005 '''Layer:''' 7 '''Operational Scale:''' Operational '''Level of Maturity:''' Proof of Concept '''Category:''' Exploit '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concepts:''' ...")
02:57, 30 July 2024 EE talk contribs created page Campbell’s Law (Created page with "== '''Campbell’s Law ''' == '''Short Description:''' Metric optimization may lead to detrimental follow on effects. '''CAT ID:''' CAT-2023-006 '''Layer:''' 9 '''Operational Scale:''' Operational '''Level of Maturity:''' Well-Established '''Category:''' Vulnerability '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concepts:''' '''Mechanism:'...")
02:56, 30 July 2024 EE talk contribs created page Training Data Poisoning Attack (Created page with "== '''Training Data Poisoning Attack ''' == '''Short Description:''' An attacker changes training data to manipulate the model to act favorably for the attacker. '''CAT ID:''' CAT-2023-007 '''Layer:''' 7 '''Operational Scale:''' Operational '''Level of Maturity:''' Proof of Concept '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related...")
02:55, 30 July 2024 EE talk contribs created page Trigger Based Attack (Created page with "== '''Trigger Based Attack ''' == '''Short Description:''' Attacker trains a model to maliciously react when a "trigger" stimuli is encountered. '''CAT ID:''' CAT-2023-008 '''Layer:''' 7 '''Operational Scale:''' Operational '''Level of Maturity:''' Proof of Concept '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concepts:''' <br...")
02:54, 30 July 2024 EE talk contribs created page Backdoor Attacks (Created page with "== '''Backdoor Attacks ''' == '''Short Description:''' The attacker surreptitiously changes the training data by adding examples with maliciously crafted cues. '''CAT ID:''' CAT-2023-009 '''Layer:''' 7 '''Operational Scale:''' Operational '''Level of Maturity:''' Proof of Concept '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Co...")
02:52, 30 July 2024 EE talk contribs created page Input Manipulation Attack (Created page with "== '''Input Manipulation Attack ''' == '''Short Description:''' Attacker deliberately alters input data to mislead a model. '''CAT ID:''' CAT-2023-010 '''Layer:''' 7 '''Operational Scale:''' Tactical '''Level of Maturity:''' Well-Established '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concepts:''' '''Mechanism:''' <b...")
02:50, 30 July 2024 EE talk contribs created page Evasion Attacks (Created page with "== '''Evasion Attacks ''' == '''Short Description:''' Attacker attemps to subvert model output by perturbing the data input into a trained model '''CAT ID:''' CAT-2023-011 '''Layer:''' 7 '''Operational Scale:''' Tactical '''Level of Maturity:''' Proof of Concept '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concepts:''' ...")
02:48, 30 July 2024 EE talk contribs created page Adversarial Examples (Created page with "== '''Adversarial Examples ''' == '''Short Description:''' Tricking AI/ML models using deceptive input data. '''CAT ID:''' CAT-2023-012 '''Layer:''' 7 '''Operational Scale:''' Tactical '''Level of Maturity:''' Proof of Concept '''Category:''' Exploit '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concepts:''' '''Mechanism:''' '''Multi...")
02:47, 30 July 2024 EE talk contribs created page Membership Inference Attack (Created page with "== '''Membership Inference Attack ''' == '''Short Description:''' An attacker is able to determine if a record was included in the model’s training. '''CAT ID:''' CAT-2023-013 '''Layer:''' 7 '''Operational Scale:''' Operational '''Level of Maturity:''' Proof of Concept '''Category:''' Exploit '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concept...")
02:42, 30 July 2024 EE talk contribs created page Model Inversion Attack (Created page with "== '''Model Inversion Attack ''' == '''Short Description:''' Attacker uses model responses to recontruct training dataset. '''CAT ID:''' CAT-2023-014 '''Layer:''' 7 '''Operational Scale:''' Operational '''Level of Maturity:''' Proof of Concept '''Category:''' Exploit '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concepts:''' '''Mechanism:'...")
02:34, 30 July 2024 EE talk contribs created page Data Reconstruction (Created page with "== '''Data Reconstruction ''' == '''Short Description:''' Attackers use model outputs to infer characteristics about the model training data. '''CAT ID:''' CAT-2023-015 '''Layer:''' 7 '''Operational Scale:''' Operational '''Level of Maturity:''' Proof of Concept '''Category:''' Exploit '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concepts:''' <b...")
02:33, 30 July 2024 EE talk contribs created page Model Theft (Created page with "== '''Model Theft ''' == '''Short Description:''' Attacker(s) emulate an AI/ML model for the purpose of unauthorized reproduction. '''CAT ID:''' CAT-2023-016 '''Layer:''' 7 '''Operational Scale:''' Operational '''Level of Maturity:''' Proof of Concept '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concepts:''' '''Mechanis...")
02:30, 30 July 2024 EE talk contribs created page Model Extraction Attacks (Created page with "== '''Model Extraction Attacks ''' == '''Short Description:''' Attacker(s) reproduce the model by repeatedly observing inputs and outputs and using these emulate the model. '''CAT ID:''' CAT-2023-017 '''Layer:''' 7 '''Operational Scale:''' Operational '''Level of Maturity:''' Proof of Concept '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Close...")
02:29, 30 July 2024 EE talk contribs created page Repeated Exposure (Created page with "== '''Repeated Exposure ''' == '''Short Description:''' Target is repeatedly exposed to a stimulus or message. '''CAT ID:''' CAT-2023-018 '''Layer:''' 8 '''Operational Scale:''' Tactical '''Level of Maturity:''' Well-Established '''Category:''' Exploit '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concepts:''' '''Mechanism:''' '''Mul...")
02:28, 30 July 2024 EE talk contribs created page Psychological Chuting (Created page with "== '''Psychological Chuting ''' == '''Short Description:''' The process of psychologically guiding a target along a specific line of thinking. '''CAT ID:''' CAT-2024-009 '''Layer:''' 8 '''Operational Scale:''' Tactical '''Level of Maturity:''' Well-Established '''Category:''' Exploit '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concepts:''' ...")
02:15, 30 July 2024 EE talk contribs created page Positive Test Strategy (Created page with "== '''Positive Test Strategy ''' == '''Short Description:''' The tendency for people to search memory for positive instances (hits) rather than lack of (misses). '''CAT ID:''' CAT-2024-008 '''Layer:''' 8 '''Operational Scale:''' Tactical '''Level of Maturity:''' Well-Established '''Category:''' Vulnerability '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely R...")
02:10, 30 July 2024 EE talk contribs created page Evil Eve Attack (Created page with "== '''Evil Eve Attack ''' == '''Short Description:''' A cognitive agent poses as a benign assistant or automated therapist eliciting information about user. '''CAT ID:''' CAT-2024-001 '''Layer:''' 8 '''Operational Scale:''' Operational '''Level of Maturity:''' Proof of Concept '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Conce...")
02:08, 30 July 2024 EE talk contribs created page Sleeper Agent Attack (Created page with "== '''Sleeper Agent Attack ''' == '''Short Description:''' An AI model acts in a benign capacity, only to act maliciously when a trigger point is encountered. '''CAT ID:''' CAT-2024-002 '''Layer:''' 7 or 8 '''Operational Scale:''' Operational '''Level of Maturity:''' Proof of Concept '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Relate...")
02:07, 30 July 2024 EE talk contribs created page False Feedback Injection (Created page with "== '''False Feedback Injection ''' == '''Short Description:''' Attacker deliberately provides false reinforcement feedback to degrade AI/ML model performance. '''CAT ID:''' CAT-2024-003 '''Layer:''' 7 '''Operational Scale:''' Operational '''Level of Maturity:''' Proof of Concept '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Co...")
02:18, 29 July 2024 EE talk contribs created page Stroop Test (Created page with "== '''Stroop Test ''' == '''Short Description:''' Use of Stroop Test to detect native language. '''CAT ID:''' CAT-2024-004 '''Layer:''' 8 '''Operational Scale:''' Tactical '''Level of Maturity:''' Observed in the Wild '''Category:''' TTP '''Subcategory:''' '''Also Known As:''' == '''Description:''' == '''Brief Description:''' '''Closely Related Concepts:''' '''Mechanism:''' '''Multipliers:''' <...")

Anonymous

Search

All public logs

Namespaces

More

Page actions

Navigation

Navigation

Wiki tools

Wiki tools

Anonymous

Search

All public logs

Navigation

Wiki tools

Page tools