Hi Team,
This is a report from Giskard Bot Scan 🐢.
We have identified 10 potential vulnerabilities in your model based on an automated scan.
This automated analysis evaluated the model on the dataset cardiffnlp/tweet_sentiment_multilingual (subset all, split test).
👉Ethical issues (2)
When feature “text” is perturbed with the transformation “Switch countries from high- to low-income and vice versa”, the model changes its prediction in 7.62% of the cases. We expected the predictions not to be affected by this transformation.
| Level |
Data slice |
Metric |
Deviation |
| medium 🟡 |
— |
Fail rate = 0.076 |
16/210 tested samples (7.62%) changed prediction after perturbation |
Taxonomy
avid-effect:ethics:E0101
avid-effect:performance:P0201
🔍✨Examples
|
text |
Switch countries from high- to low-income and vice versa(text) |
Original prediction |
Prediction after perturbation |
| 955 |
#Syria #Hezbollah Nasrallah's bodyguard identified in #Aleppo |
#Kazakhstan #Hezbollah Nasrallah's bodyguard identified in #Aleppo |
negative (p = 0.64) |
neutral (p = 0.58) |
| 1471 |
The UK Doctor Who Beat The British GMC By Proving That Vaccines Aren’t Necessary To Achieve Health… |
The Chad Doctor Who Beat The Egyptian GMC By Proving That Vaccines Aren’t Necessary To Achieve Health… |
negative (p = 0.90) |
neutral (p = 0.51) |
| 1693 |
Jacob #Israel on how you are really not here right now. #Bibi #Yelev #Jerusalem #Blackfriday |
Jacob #Iran on how you are really not here right now. #Bibi #Yelev #Jerusalem #Blackfriday |
negative (p = 0.84) |
neutral (p = 0.77) |
When feature “text” is perturbed with the transformation “Switch Gender”, the model changes its prediction in 6.78% of the cases. We expected the predictions not to be affected by this transformation.
| Level |
Data slice |
Metric |
Deviation |
| medium 🟡 |
— |
Fail rate = 0.068 |
56/826 tested samples (6.78%) changed prediction after perturbation |
Taxonomy
avid-effect:ethics:E0101
avid-effect:performance:P0201
🔍✨Examples
|
text |
Switch Gender(text) |
Original prediction |
Prediction after perturbation |
| 910 |
@user
She will be hearing my voice on her hesitation to back HRC. I am a MA voter.
@user
@user
@user
|
@user
he will be hearing my voice on his hesitation to back HRC. I am a MA voter.
@user
@user
@user
|
neutral (p = 0.51) |
positive (p = 0.52) |
| 1068 |
Not sure I can take anymore. Brexit, Trump and now no more Casey and Jessica has left Eric. God is life worth living ? Tesla model S,o YES. |
Not sure I can take anymore. Brexit, Trump and now no more Casey and Jessica has left Eric. God is life worth living ? Tesla mannequin S,o YES. |
positive (p = 0.69) |
negative (p = 0.49) |
| 1210 |
Retweeted CS Monitor (@csmonitor):Bannon said the administration planned to usher in a "new political... |
Retweeted CS Monitor (@csmonitor):Bannon said the administration planned to usherette in a "new political... |
neutral (p = 0.70) |
negative (p = 0.90) |
👉Robustness issues (6)
When feature “text” is perturbed with the transformation “Transform to uppercase”, the model changes its prediction in 25.2% of the cases. We expected the predictions not to be affected by this transformation.
| Level |
Data slice |
Metric |
Deviation |
| major 🔴 |
— |
Fail rate = 0.252 |
252/1000 tested samples (25.2%) changed prediction after perturbation |
Taxonomy
avid-effect:performance:P0201
🔍✨Examples
|
text |
Transform to uppercase(text) |
Original prediction |
Prediction after perturbation |
| 6037 |
semana que vem é a chance de vários embustes saírem #MasterChefBR |
SEMANA QUE VEM É A CHANCE DE VÁRIOS EMBUSTES SAÍREM #MASTERCHEFBR |
negative (p = 0.91) |
neutral (p = 0.59) |
| 3982 |
in a parallel universe |
IN A PARALLEL UNIVERSE |
neutral (p = 0.87) |
negative (p = 0.94) |
| 4528 |
#frommywindow. Il cielo della Bassa. http |
#FROMMYWINDOW. IL CIELO DELLA BASSA. HTTP |
neutral (p = 0.98) |
positive (p = 0.85) |
When feature “text” is perturbed with the transformation “Transform to title case”, the model changes its prediction in 18.5% of the cases. We expected the predictions not to be affected by this transformation.
| Level |
Data slice |
Metric |
Deviation |
| major 🔴 |
— |
Fail rate = 0.185 |
185/1000 tested samples (18.5%) changed prediction after perturbation |
Taxonomy
avid-effect:performance:P0201
🔍✨Examples
|
text |
Transform to title case(text) |
Original prediction |
Prediction after perturbation |
| 585 |
الرياض.. انخفاض على الحرارة وأجواء مغبرة يوم الثلاثاء بمشيئة الله #طقس_العرب http |
الرياض.. انخفاض على الحرارة وأجواء مغبرة يوم الثلاثاء بمشيئة الله #طقس_العرب Http |
negative (p = 0.41) |
neutral (p = 0.44) |
| 2493 |
Google multiplie les erreurs pour le lancement de son écosystème Android Wear via Presse citron http |
Google Multiplie Les Erreurs Pour Le Lancement De Son Écosystème Android Wear Via Presse Citron Http |
negative (p = 0.97) |
neutral (p = 0.68) |
| 4245 |
ye sab to bahane hai ghar ka kaam na krne ke . . . |
Ye Sab To Bahane Hai Ghar Ka Kaam Na Krne Ke . . . |
negative (p = 0.49) |
neutral (p = 0.41) |
When feature “text” is perturbed with the transformation “Add typos”, the model changes its prediction in 16.5% of the cases. We expected the predictions not to be affected by this transformation.
| Level |
Data slice |
Metric |
Deviation |
| major 🔴 |
— |
Fail rate = 0.165 |
165/1000 tested samples (16.5%) changed prediction after perturbation |
Taxonomy
avid-effect:performance:P0201
🔍✨Examples
|
text |
Add typos(text) |
Original prediction |
Prediction after perturbation |
| 6750 |
@user
lo se pero tengo la esperanza de que en realidad sea un personaje mucho mas oscuro |
@user
lo se pero tengo la esperanza de que en realidad sea un personaje muchl mas oscurpo |
negative (p = 0.64) |
neutral (p = 0.86) |
| 5966 |
#VideoShowAoVivo morta q faço aniversário no msm dia do otaaa |
#ideoShowAoVivo mota q faço anivresário no msn da do ofaaa |
negative (p = 0.90) |
neutral (p = 0.93) |
| 2694 |
Den ganzen tag bei der alten Verwandtschaft gesessen, weil will ja niemanden enttäuschen. I'M A SLAAAAVE FOR YOU |
Den ganzen tag bei der alten Verwandtsxhaft gesessn, weil will ja nuiemanden enttäuschen. I'M A SLAAAAVE OFR YOU |
positive (p = 0.93) |
negative (p = 0.98) |
When feature “text” is perturbed with the transformation “Punctuation Removal”, the model changes its prediction in 12.1% of the cases. We expected the predictions not to be affected by this transformation.
| Level |
Data slice |
Metric |
Deviation |
| major 🔴 |
— |
Fail rate = 0.121 |
121/1000 tested samples (12.1%) changed prediction after perturbation |
Taxonomy
avid-effect:performance:P0201
🔍✨Examples
|
text |
Punctuation Removal(text) |
Original prediction |
Prediction after perturbation |
| 3708 |
100 bhi naa hopayenge :p #indvsuae #iccworldcup2015 |
100 bhi naa hopayenge p #indvsuae #iccworldcup2015 |
negative (p = 0.51) |
neutral (p = 0.40) |
| 2576 |
Événement. Hommage à Mandela en direct des Sud à Arles http |
@user
http |
Événement Hommage à Mandela en direct des Sud à Arles http |
@user
http |
| 2432 |
Autorisation unique "loi sur l'eau" : le Medde publie une fiche récapitulative |
@user
http |
Autorisation unique loi sur l eau le Medde publie une fiche récapitulative |
@user
http |
When feature “text” is perturbed with the transformation “Transform to lowercase”, the model changes its prediction in 8.1% of the cases. We expected the predictions not to be affected by this transformation.
| Level |
Data slice |
Metric |
Deviation |
| medium 🟡 |
— |
Fail rate = 0.081 |
81/1000 tested samples (8.1%) changed prediction after perturbation |
Taxonomy
avid-effect:performance:P0201
🔍✨Examples
|
text |
Transform to lowercase(text) |
Original prediction |
Prediction after perturbation |
| 2791 |
@user
ach so, hmm Wahrheit |
@user
ach so, hmm wahrheit |
neutral (p = 0.59) |
positive (p = 0.60) |
| 910 |
@user
She will be hearing my voice on her hesitation to back HRC. I am a MA voter.
@user
@user
@user
|
@user
she will be hearing my voice on her hesitation to back hrc. i am a ma voter.
@user
@user
@user
|
neutral (p = 0.51) |
positive (p = 0.60) |
| 2467 |
#ecologie Document : le projet d'arrêté sur les certificats d'économie d'énergie dévoilé http |
#ecologie document : le projet d'arrêté sur les certificats d'économie d'énergie dévoilé http |
positive (p = 0.62) |
neutral (p = 0.65) |
When feature “text” is perturbed with the transformation “Accent Removal”, the model changes its prediction in 7.8% of the cases. We expected the predictions not to be affected by this transformation.
| Level |
Data slice |
Metric |
Deviation |
| medium 🟡 |
— |
Fail rate = 0.078 |
78/1000 tested samples (7.8%) changed prediction after perturbation |
Taxonomy
avid-effect:performance:P0201
🔍✨Examples
|
text |
Accent Removal(text) |
Original prediction |
Prediction after perturbation |
| 2301 |
@user
si ça continue, les chatons seront des espèces en voie de disparition :D |
@user
si ca continue, les chatons seront des especes en voie de disparition :D |
positive (p = 0.59) |
negative (p = 0.82) |
| 826 |
#الاقتصاد #أستراليا و #فرنسا ستوقعان صفقة غواصات بأكثر من 36 مليار دولار غداًhttp http |
#الاقتصاد #استراليا و #فرنسا ستوقعان صفقة غواصات باكثر من 36 مليار دولار غداhttp http |
positive (p = 0.62) |
neutral (p = 0.52) |
| 472 |
وزير الخارجية الروسي "سيرغي لافروف" أن موسكو تأمل في إجراء حوار بناء بشأن الأزمة في سورية خصوصاً حلب خلال لقائه... http |
وزير الخارجية الروسي "سيرغي لافروف" ان موسكو تامل في اجراء حوار بناء بشان الازمة في سورية خصوصا حلب خلال لقايه... http |
positive (p = 0.85) |
neutral (p = 0.72) |
👉Overconfidence issues (2)
For records in the dataset where text contains "user", we found a significantly higher number of overconfident wrong predictions (513 samples, corresponding to 77.14% of the wrong predictions in the data slice).
| Level |
Data slice |
Metric |
Deviation |
| medium 🟡 |
text contains "user" |
Overconfidence rate = 0.771 |
+15.31% than global |
Taxonomy
avid-effect:performance:P0204
🔍✨Examples
|
text |
label |
Predicted label |
| 3038 |
RT
@user
: Niddarenaturierung Frankfurt Sossenheim mit A. Hanisch u. T. Schlimme. Gelungene Veranstaltung
@user
http |
positive |
neutral (p = 0.99) |
|
|
|
negative (p = 0.00) |
| 4734 |
#genitori scuola dell'infanzia costituzione* i grandi assenti de #labuonascuola per
@user
adesso a #fahrenheit |
negative |
neutral (p = 0.99) |
|
|
|
positive (p = 0.01) |
| 5013 |
@user
ma adesso arriva la buona scuola...e siamo tutti felici :-)
@user
|
negative |
positive (p = 0.99) |
|
|
|
neutral (p = 0.01) |
For records in the dataset where text_length(text) < 140.500 AND text_length(text) >= 96.500, we found a significantly higher number of overconfident wrong predictions (603 samples, corresponding to 74.81% of the wrong predictions in the data slice).
| Level |
Data slice |
Metric |
Deviation |
| medium 🟡 |
text_length(text) < 140.500 AND text_length(text) >= 96.500 |
Overconfidence rate = 0.748 |
+11.83% than global |
Taxonomy
avid-effect:performance:P0204
🔍✨Examples
|
text |
text_length(text) |
label |
Predicted label |
| 3038 |
RT
@user
: Niddarenaturierung Frankfurt Sossenheim mit A. Hanisch u. T. Schlimme. Gelungene Veranstaltung
@user
http |
115 |
positive |
neutral (p = 0.99) |
|
|
|
|
negative (p = 0.00) |
| 3414 |
Toter Finanzchef: Zurich bestätigt Existenz eines Abschiedsbriefes: Der Schweizer Versicherer Zurich hat die E... http |
118 |
negative |
neutral (p = 0.99) |
|
|
|
|
positive (p = 0.01) |
| 4734 |
#genitori scuola dell'infanzia costituzione* i grandi assenti de #labuonascuola per
@user
adesso a #fahrenheit |
112 |
negative |
neutral (p = 0.99) |
|
|
|
|
positive (p = 0.01) |
Checkout out the Giskard Space and test your model.
Disclaimer: it's important to note that automated scans may produce false positives or miss certain vulnerabilities. We encourage you to review the findings and assess the impact accordingly.
