119 lines
6.1 KiB
JSON
119 lines
6.1 KiB
JSON
{
|
||
"predicates": [
|
||
{
|
||
"expanded": "Intentionally-Motivated Failures Summary",
|
||
"description": "Intentional failures wherein the failure is caused by an active adversary attempting to subvert the system to attain her goals – either to misclassify the result, infer private training data, or to steal the underlying algorithm.",
|
||
"value": "intentionally-motivated-failures-summary"
|
||
},
|
||
{
|
||
"description": "Unintentional failures wherein the failure is because an ML system produces a formally correct but completely unsafe outcome.",
|
||
"expanded": "Unintended Failures Summary",
|
||
"value": "unintended-failures-summary"
|
||
}
|
||
],
|
||
"values": [
|
||
{
|
||
"predicate": "intentionally-motivated-failures-summary",
|
||
"entry": [
|
||
{
|
||
"value": "1-perturbation-attack",
|
||
"expanded": "Perturbation attack",
|
||
"description": "Attacker modifies the query to get appropriate response. It doesn't violate traditional technological notion of access/authorization."
|
||
},
|
||
{
|
||
"value": "2-poisoning-attack",
|
||
"expanded": "Poisoning attack",
|
||
"description": "Attacker contaminates the training phase of ML systems to get intended result. It doesn't violate traditional technological notion of access/authorization."
|
||
},
|
||
{
|
||
"value": "3-model-inversion",
|
||
"expanded": "Model Inversion",
|
||
"description": "Attacker recovers the secret features used in the model by through careful queries. It doesn't violate traditional technological notion of access/authorization."
|
||
},
|
||
{
|
||
"value": "4-membership-inference",
|
||
"expanded": "Membership Inference",
|
||
"description": "Attacker can infer if a given data record was part of the model’s training dataset or not. It doesn't violate traditional technological notion of access/authorization."
|
||
},
|
||
{
|
||
"value": "5-model-stealing",
|
||
"expanded": "Model Stealing",
|
||
"description": "Attacker is able to recover the model through carefully-crafted queries. It doesn't violate traditional technological notion of access/authorization."
|
||
},
|
||
{
|
||
"value": "6-reprogramming-ML-system",
|
||
"expanded": "Reprogramming ML system",
|
||
"description": "Repurpose the ML system to perform an activity it was not programmed for. It doesn't violate traditional technological notion of access/authorization."
|
||
},
|
||
{
|
||
"value": "7-adversarial-example-in-physical-domain",
|
||
"expanded": "Adversarial Example in Physical Domain ",
|
||
"description": "Repurpose the ML system to perform an activity it was not programmed for. It doesn't violate traditional technological notion of access/authorization."
|
||
},
|
||
{
|
||
"value": "8-malicious-ML-provider-recovering-training-data",
|
||
"expanded": "Malicious ML provider recovering training data",
|
||
"description": "Malicious ML provider can query the model used by customer and recover customer’s training data. It does violate traditional technological notion of access/authorization."
|
||
},
|
||
{
|
||
"value": "9-attacking-the-ML-supply-chain",
|
||
"expanded": "Attacking the ML supply chain",
|
||
"description": "Attacker compromises the ML models as it is being downloaded for use. It does violate traditional technological notion of access/authorization."
|
||
},
|
||
{
|
||
"value": "10-backdoor-ML",
|
||
"expanded": "Backdoor ML",
|
||
"description": "Malicious ML provider backdoors algorithm to activate with a specific trigger. It does violate traditional technological notion of access/authorization."
|
||
},
|
||
{
|
||
"value": "10-exploit-software-dependencies",
|
||
"expanded": "Exploit Software Dependencies",
|
||
"description": "Attacker uses traditional software exploits like buffer overflow to confuse/control ML systems. It does violate traditional technological notion of access/authorization."
|
||
}
|
||
]
|
||
},
|
||
{
|
||
"predicate": "unintended-failures-summary",
|
||
"entry": [
|
||
{
|
||
"value": "12-reward-hacking",
|
||
"expanded": "Reward Hacking",
|
||
"description": "Reinforcement Learning (RL) systems act in unintended ways because of mismatch between stated reward and true reward"
|
||
},
|
||
{
|
||
"value": "13-side-effects",
|
||
"expanded": "Side Effects",
|
||
"description": "RL system disrupts the environment as it tries to attain its goal"
|
||
},
|
||
{
|
||
"value": "14-distributional-shifts",
|
||
"expanded": "Distributional shifts",
|
||
"description": "The system is tested in one kind of environment, but is unable to adapt to changes in other kinds of environment"
|
||
},
|
||
{
|
||
"value": "15-natural-adversarial-examples",
|
||
"expanded": "Natural Adversarial Examples",
|
||
"description": "Without attacker perturbations, the ML system fails owing to hard negative mining"
|
||
},
|
||
{
|
||
"value": "16-common-corruption",
|
||
"expanded": "Common Corruption",
|
||
"description": "The system is not able to handle common corruptions and perturbations such as tilting, zooming, or noisy images"
|
||
},
|
||
{
|
||
"value": "17-incomplete-testing",
|
||
"expanded": "Incomplete Testing",
|
||
"description": "The ML system is not tested in the realistic conditions that it is meant to operate in"
|
||
}
|
||
]
|
||
}
|
||
],
|
||
"refs": [
|
||
"https://docs.microsoft.com/en-us/security/failure-modes-in-machine-learning"
|
||
],
|
||
"version": 1,
|
||
"description": "The purpose of this taxonomy is to jointly tabulate both the of these failure modes in a single place. Intentional failures wherein the failure is caused by an active adversary attempting to subvert the system to attain her goals – either to misclassify the result, infer private training data, or to steal the underlying algorithm. Unintentional failures wherein the failure is because an ML system produces a formally correct but completely unsafe outcome.",
|
||
"expanded": "Failure mode in machine learning.",
|
||
"namespace": "failure-mode-in-machine-learning"
|
||
}
|