Artificial Intelligence Policy Tracker

AI risk

AI attacks and incidents: the record in charts

What has gone wrong with AI, who caused it, whether it was meant, and how that compares with the risks that frameworks describe. Every figure is a count of records in the AI Incident Database or the MIT AI Risk Repository. "Attack" here means an incident coded as deliberate. This page has no list of records: those are on the pages it links to.

Incidents classified under MIT domain 2 (Privacy & Security) or domain 4 (Malicious Actors & Misuse): privacy compromise, attacks on AI systems, fraud and scams, disinformation and surveillance, cyberattacks and weapons.

Synced 1,708 incidents on record newest dated 28 Sep 2026 classified to February 2026 No new record has arrived from the daily sync for 49 days; the figures stop there

In brief

678 of the 1,496 classified incidents in the AI Incident Database (45%) fall under the two MIT risk domains for security and malicious use. 243 are dated in the 12 months to February 2026, up 21% on the 201 of the 12 months before. 128 newer incidents are recorded but not yet classified, so comparisons stop at February 2026.

Incidents in view
678
45% of the 1,496 classified
12 months to February 2026
243
+21% on the 12 months before (201)
Coded deliberate
87%
of 678 incidents with an intent code
Risk entries, same coding
468
from 74 frameworks, MIT AI Risk Repository
Not yet classified
128
incidents dated after February 2026

1. Rising: up 21% in the 12 months to February 2026

243 incidents under the security and malicious-use domains are dated in the 12 months to February 2026, against 201 in the 12 months before. The comparison stops at February 2026 on purpose: 128 newer incidents are on record without a classification, and counting those months would show a fall that is only a backlog.

Incidents per month, 36 monthsBy date of the incident. A month counts as classified once 75% of its incidents carry a code.
Incidents per month, 36 months 47 24 classified to Feb 2026 Oct 2023: 11 security and malicious use of 18 recorded Oct 2023: 11 security and malicious use of 18 recorded Nov 2023: 2 security and malicious use of 10 recorded Nov 2023: 2 security and malicious use of 10 recorded Dec 2023: 13 security and malicious use of 22 recorded Dec 2023: 13 security and malicious use of 22 recorded Jan 2024: 8 security and malicious use of 17 recorded Jan 2024: 8 security and malicious use of 17 recorded Jan 2024 Feb 2024: 15 security and malicious use of 27 recorded Feb 2024: 15 security and malicious use of 27 recorded Mar 2024: 15 security and malicious use of 20 recorded Mar 2024: 15 security and malicious use of 20 recorded Apr 2024: 15 security and malicious use of 36 recorded Apr 2024: 15 security and malicious use of 36 recorded May 2024: 11 security and malicious use of 25 recorded May 2024: 11 security and malicious use of 25 recorded Jun 2024: 10 security and malicious use of 26 recorded Jun 2024: 10 security and malicious use of 26 recorded Jul 2024: 15 security and malicious use of 25 recorded Jul 2024: 15 security and malicious use of 25 recorded Jul Aug 2024: 15 security and malicious use of 24 recorded Aug 2024: 15 security and malicious use of 24 recorded Sep 2024: 20 security and malicious use of 28 recorded Sep 2024: 20 security and malicious use of 28 recorded Oct 2024: 18 security and malicious use of 34 recorded Oct 2024: 18 security and malicious use of 34 recorded Nov 2024: 11 security and malicious use of 18 recorded Nov 2024: 11 security and malicious use of 18 recorded Dec 2024: 19 security and malicious use of 26 recorded Dec 2024: 19 security and malicious use of 26 recorded Jan 2025: 20 security and malicious use of 32 recorded Jan 2025: 20 security and malicious use of 32 recorded Jan 2025 Feb 2025: 32 security and malicious use of 47 recorded Feb 2025: 32 security and malicious use of 47 recorded Mar 2025: 29 security and malicious use of 44 recorded Mar 2025: 29 security and malicious use of 44 recorded Apr 2025: 29 security and malicious use of 47 recorded Apr 2025: 29 security and malicious use of 47 recorded May 2025: 21 security and malicious use of 34 recorded May 2025: 21 security and malicious use of 34 recorded Jun 2025: 26 security and malicious use of 44 recorded Jun 2025: 26 security and malicious use of 44 recorded Jul 2025: 21 security and malicious use of 39 recorded Jul 2025: 21 security and malicious use of 39 recorded Jul Aug 2025: 19 security and malicious use of 35 recorded Aug 2025: 19 security and malicious use of 35 recorded Sep 2025: 9 security and malicious use of 17 recorded Sep 2025: 9 security and malicious use of 17 recorded Oct 2025: 19 security and malicious use of 41 recorded Oct 2025: 19 security and malicious use of 41 recorded Nov 2025: 16 security and malicious use of 28 recorded Nov 2025: 16 security and malicious use of 28 recorded Dec 2025: 20 security and malicious use of 44 recorded Dec 2025: 20 security and malicious use of 44 recorded Jan 2026: 20 security and malicious use of 38 recorded Jan 2026: 20 security and malicious use of 38 recorded Jan 2026 Feb 2026: 14 security and malicious use of 30 recorded Feb 2026: 14 security and malicious use of 30 recorded Mar 2026: 12 security and malicious use of 27 recorded (classification incomplete) Mar 2026: 12 security and malicious use of 27 recorded (classification incomplete) Apr 2026: 7 security and malicious use of 25 recorded (classification incomplete) Apr 2026: 7 security and malicious use of 25 recorded (classification incomplete) May 2026: 7 security and malicious use of 35 recorded (classification incomplete) May 2026: 7 security and malicious use of 35 recorded (classification incomplete) Jun 2026: 0 security and malicious use of 23 recorded (classification incomplete) Jul 2026: 0 security and malicious use of 33 recorded (classification incomplete) Jul Aug 2026: 0 security and malicious use of 13 recorded (classification incomplete) Sep 2026: 0 security and malicious use of 15 recorded (classification incomplete)
  • Security and malicious use
  • All recorded incidents
  • Classification incomplete
Incidents per month, 36 months
MonthSecurity and malicious useAll recorded incidentsClassification
2023-101118complete
2023-11210complete
2023-121322complete
2024-01817complete
2024-021527complete
2024-031520complete
2024-041536complete
2024-051125complete
2024-061026complete
2024-071525complete
2024-081524complete
2024-092028complete
2024-101834complete
2024-111118complete
2024-121926complete
2025-012032complete
2025-023247complete
2025-032944complete
2025-042947complete
2025-052134complete
2025-062644complete
2025-072139complete
2025-081935complete
2025-09917complete
2025-101941complete
2025-111628complete
2025-122044complete
2026-012038complete
2026-021430complete
2026-031227incomplete
2026-04725incomplete
2026-05735incomplete
2026-06023incomplete
2026-07033incomplete
2026-08013incomplete
2026-09015incomplete

2. Who was responsible, was it meant, and what kind of harm

The widest path is a person acting with deliberate effect: 398 of the 678 classified incidents in view (59%). Follow a colour from left to right to see where deliberate and accidental incidents end up.

From cause to harm: responsible entity, intent and risk domainMIT causal and domain taxonomies, as applied by the AI Incident Database
From cause to harm: responsible entity, intent and risk domain RESPONSIBLE INTENT RISK DOMAIN Human → Deliberate: 398 (59%) Human → Accidental: 18 (3%) Human → Unclear: 1 (0%) AI → Deliberate: 192 (28%) AI → Accidental: 63 (9%) AI → Unclear: 3 (0%) Other → Deliberate: 1 (0%) Other → Unclear: 2 (0%) Deliberate → Privacy & Security: 53 (8%) Deliberate → Malicious actors: 538 (79%) Accidental → Privacy & Security: 55 (8%) Accidental → Malicious actors: 26 (4%) Unclear → Privacy & Security: 4 (1%) Unclear → Malicious actors: 2 (0%) Human 417 AI 258 Other 3 Deliberate 591 · 87% Accidental 81 · 12% Unclear 6 · 1% 2 Privacy & Security 112 4 Malicious actors 566
  • Deliberate (coded Intentional)
  • Accidental (coded Unintentional)
  • Unclear (coded Other)
From cause to harm: responsible entity, intent and risk domain
FromToIncidents
AIAccidental63
AIDeliberate192
AIUnclear3
HumanDeliberate398
HumanAccidental18
HumanUnclear1
OtherDeliberate1
OtherUnclear2
AccidentalPrivacy & Security55
AccidentalMalicious actors26
DeliberateMalicious actors538
DeliberatePrivacy & Security53
UnclearMalicious actors2
UnclearPrivacy & Security4

From accident to attack, year by year

In 2020, 76% of the classified incidents in view were coded deliberate; in 2025, 89%. Deliberate incidents sit at the base of each column, so their growth reads against the whole.

Classified incidents per year, by intentYear of the incident
Classified incidents per year, by intent 261 2019 · Deliberate: 9 of 11 2019 · Accidental: 2 of 11 82% 2019 2020 · Deliberate: 16 of 21 2020 · Accidental: 5 of 21 76% 2020 2021 · Deliberate: 9 of 12 2021 · Accidental: 3 of 12 75% 2021 2022 · Deliberate: 27 of 30 2022 · Accidental: 3 of 30 90% 2022 2023 · Deliberate: 69 of 77 2023 · Accidental: 7 of 77 2023 · Unclear: 1 of 77 90% 2023 2024 · Deliberate: 159 of 172 2024 · Accidental: 11 of 172 2024 · Unclear: 2 of 172 92% 2024 2025 · Deliberate: 231 of 261 2025 · Accidental: 29 of 261 2025 · Unclear: 1 of 261 89% 2025 2026 · Deliberate: 50 of 60 2026 · Accidental: 8 of 60 2026 · Unclear: 2 of 60 83% 2026*
  • Deliberate
  • Accidental
  • Unclear
  • Figure over each column: share coded deliberate. * part year.
Classified incidents per year, by intent
YearDeliberateAccidentalUnclear
2019920
20201650
2021930
20222730
20236971
2024159112
2025231291
20265082

3. Where incidents concentrate, year by year

The eight kinds of incident with the most records in view. A darker cell is a larger count. The last column is a part year, and its newest incidents are not classified yet.

Incidents by risk subdomain and year of the incident
Incidents by risk subdomain and year of the incident
Subdomain \ Year20192020202120222023202420252026
4.3 Fraud, scams, and targeted manipulation 3 9 4 13 43 103 190 40
4.1 Disinformation, surveillance, and influence at scale 2 6 3 6 21 50 38 8
2.1 Compromise of privacy by obtaining, leaking or correctly inferring sensitive information 5 5 5 8 9 14 19 4
2.2 AI system security vulnerabilities and attacks 1 — — 2 3 3 5 7
4.2 Cyberattacks, weapon development or use, and mass harm — 1 — 1 1 2 9 —

4. What is described against what is recorded

The MIT AI Risk Repository codes 468 risk entries from 74 frameworks to the same subdomains as the incidents in view. Where the two shares differ, either the frameworks are ahead of the record or the record is ahead of the frameworks.

Risk subdomains: share of risk entries against share of incidentsSelect a bubble to open the subdomain
  • 2 Privacy & Security
  • 4 Malicious actors
  • Bubble size: incidents recorded. Dashed line: equal shares. Square-root scale. Unlabelled bubbles are named when pointed at.
Risk subdomains: share of risk entries against share of incidents
SubdomainShare of incidents (%)IncidentsShare of risk entries (%)Risk entries
4.3 Fraud, scams, and targeted manipulation60.941216.577
4.1 Disinformation, surveillance, and influence at scale20.413817.984
2.1 Compromise of privacy by obtaining, leaking or correctly inferring sensitive information138817.180
2.2 AI system security vulnerabilities and attacks3.52423.9112
4.2 Cyberattacks, weapon development or use, and mass harm2.21517.582
How incidents arise, against how frameworks expect them toPercent of the records that carry the code
  • Incidents recorded
  • Risk entries described

Responsible

A person
62%Incidents recorded
67%Risk entries described
An AI system
38%Incidents recorded
18%Risk entries described
Other or unclear
0%Incidents recorded
15%Risk entries described

Intent

Deliberate
87%Incidents recorded
69%Risk entries described
Accidental
12%Incidents recorded
14%Risk entries described
Other or unclear
1%Incidents recorded
17%Risk entries described

Timing

After release
98%Incidents recorded
76%Risk entries described
Before release
2%Incidents recorded
8%Risk entries described
Other or unclear
0%Incidents recorded
16%Risk entries described

5. Who is harmed, and by what

The parties named most often as harmed, or nearly harmed, in the classified incidents in view, and the kind of risk behind each. Read a row as that party's risk profile and a column as the parties one kind of risk reaches. The record names values (epistemic integrity, privacy) as well as people, and a name is an allegation in a report, not a finding.

Who is harmed, by kind of riskCell: incidents. Shading: share of the row.
Who is harmed, by kind of risk. Each cell is the number of incidents; the shading is its share of the row.
Harmed party 1Discrimination & Toxicity 2Privacy & Security 3Misinformation 4Malicious actors 5Human-Computer Interaction 6Socioeconomic & Environmental 7AI system safety, failures, & limitations Incidents
Epistemic Integrity · 5 · 178 · · · 183
General Public · 10 · 151 · · · 161
Privacy · 68 · 35 · · · 103
Democratic Integrity · · · 62 · · · 62
National Security And Intelligence Stakeholders · 2 · 44 · · · 46
Students · 3 · 41 · · · 44
Minors · 9 · 31 · · · 40
Women and girls · 2 · 36 · · · 38
  • 1 Discrimination & Toxicity
  • 2 Privacy & Security
  • 3 Misinformation
  • 4 Malicious actors
  • 5 Human-Computer Interaction
  • 6 Socioeconomic & Environmental
  • 7 AI system safety, failures, & limitations

6. Where to look first

The questions a risk owner brings to this record, answered from the counts above. Each answer describes the record, not your exposure: use it to choose which subdomain to open.

Which kind of incident is recorded most?

4.3 Fraud, scams, and targeted manipulation: 163 of the 243 incidents under the security and malicious-use domains dated in the 12 months to February 2026 (67%).

Open 4.3: definition, frameworks and incidents

Which is growing fastest?

4.2 Cyberattacks, weapon development or use, and mass harm: 9 incidents in the 12 months to February 2026, against 2 in the 12 months before. The counts are small, so read it as a signal to watch and not as a rate.

Open 4.2: definition, frameworks and incidents

What is recorded more often than the frameworks describe?

4.3 Fraud, scams, and targeted manipulation is 61% of the classified incidents here and 17% of the 468 matching risk entries in the MIT AI Risk Repository.

Open 4.3: definition, frameworks and incidents

What is described far more than it is recorded?

2.2 AI system security vulnerabilities and attacks: 24% of the risk entries and 3.5% of the incidents (24). A low count is not a low risk: a harm that has not happened yet, or is not reported, leaves no record.

Open 2.2: definition, frameworks and incidents

Is deliberate misuse or accident the larger share?

In the 12 months to February 2026, 86% of the classified incidents were coded deliberate (209 of 243), against 93% in the 12 months before.

The board: one card for each kind of incident

Every kind with at least 10 records in view, busiest first. The label on each card is worked out from two counts, by the rules under the cards.

Rising
at least 10 incidents in the last 12 months and up 25% or more on the 12 before.
Steady
at least 10 incidents in the last 12 months and within 25% of the 12 before.
Easing
at least 10 incidents in the 12 months before and down 25% or more since.
Emerging
fewer than 10 incidents in the last 12 months, at least three, and more than in the 12 before.
Sparse
too few recent incidents to state a direction.

7. What the rules on record cover

The same seven risk domains twice: the incidents in view, and the policy instruments in this tracker whose recorded use cases fall in that domain. An instrument can count under more than one domain. A long bar on the left beside a short one on the right is a question to ask, not a finding that the rules are missing.

Incidents in view, by risk domainClassified incidents only
1 Discrimination & Toxicity
0
2 Privacy & Security
112
3 Misinformation
0
4 Malicious actors
566
5 Human-Computer Interaction
0
6 Socioeconomic & Environmental
0
7 AI system safety, failures, & limitations
0
Instruments on record, by risk domainPublished instruments, by recorded use case
1 Discrimination & Toxicity
25
2 Privacy & Security
16
3 Misinformation
50
4 Malicious actors
52
5 Human-Computer Interaction
56
6 Socioeconomic & Environmental
142
7 AI system safety, failures, & limitations
52

How to read this page

  • These are reports, not a census. An incident is on record because someone wrote about it and an editor added it. Coverage leans toward English-language media, and a count is not a rate.
  • Classification trails the record. The codes for intent, entity and risk domain are added after an incident is recorded. A month is compared only when 75% of its incidents carry a code, which is why the year-on-year figures here end before the newest incident and differ from the calendar figure on AI risk.
  • "Deliberate" is a code, not a verdict. It is the MIT causal taxonomy's "Intentional": the outcome was the expected result of pursuing a goal. It covers fraud and impersonation as well as attacks on AI systems themselves.
  • Risk entries are counted the same way as the incidents in view. For "Deliberate misuse" only entries coded Intentional are counted; for "Security and malicious use" only entries in domains 2 and 4.
  • Updates. Incidents are synced from the AI Incident Database once a day and from its weekly export. Nothing on this page is fetched from the source while you read it.

Disclaimer: informational only, not legal advice. Verify every claim against the linked official sources and consult a qualified lawyer before acting.