Sauvik Das
sauvik.me
Sauvik Das
@sauvik.me
I work on human-centered {security|privacy|computing}. Associate Professor (w/o tenure) at @hcii.cmu.edu. Director of the SPUD (Security, Privacy, Usability, and Design) Lab. Non-Resident Fellow @cendemtech.bsky.social
Two spuddies will be at #CSCW2025:

@yuxiwu.com will present our work on designing citizen harm reporting interfaces for privacy (and is on the job market!).

Isadora Krsek will present our work on user reactions to AI-identified self-disclosure risks online.
October 20, 2025 at 1:49 PM
The 1st Human-Centered AI, Privacy, and Security (#HAIPS2025) workshop at CCS will happen on Oct 17th! We have two amazing keynote speakers (@pgk.bsky.social and @jas0nh0ng.bsky.social), and a slate of insightful and provocative papers.

Agenda here: haips.com/#dates

#CCS2025 #AcademicSky
October 13, 2025 at 1:00 PM
📣 Accepted to #AIES2025: What do the audio datasets powering generative audio models actually contain? (led by @willie-agnew.bsky.social)

Answer: Lots of old audio content that is mostly English, often biased, and of dubious copyright / permissioning status.

Paper: www.sauvik.me/papers/65/s...
September 27, 2025 at 9:05 PM
Importantly, we found that Imago Obscura helps *address* privacy risks without impacting sharing intent.

People believed it *greatly* reduced privacy risks for images they previously wanted to share but did not share for privacy reasons, with no difference in sharing intent.
September 26, 2025 at 1:58 PM
In a summative evaluation, we found that Imago Obscura effectively improved users' awareness of / motivation to address / ability to address key privacy risks in images they wanted to share online.
September 26, 2025 at 1:58 PM
It can identify when the background of an image might uniquely identify a user's location and replace it to mitigate that risk.

It can recognize when bystanders may be in the background of a photo and provides simple mechanisms to replace those bystanders.
September 26, 2025 at 1:58 PM
Examples: Imago Obscura flags content that could uniquely identify an individual, like an obvious tattoo, and can generate realistic and less identifiable replacements.

It also identifies information that a user might consider confidential, and can obfuscate it via, e.g., blurring.
September 26, 2025 at 1:58 PM
A longstanding usable privacy challenge is helping users understand and address privacy risks in personal images they share online, from location risks to bystander risks.

Imago Obscura lets users bring-their-own-threat model, and then helps identify and address specific risks.
September 26, 2025 at 1:58 PM
🔐 New #UIST2025 paper by @kyzyl.me

Imago Obscura uses #vision #language #models to understand user #privacy concerns, improve their awareness of image privacy risks, and their ability to address these risks.

📜: sauvik.me/papers/66/se...
🔗: cmu-spuds.github.io/imago-obscura/

#PrivacySky
September 26, 2025 at 1:58 PM
Honestly, now I want to write a piper titled: "[mention a specific relevant paper by them]"
September 18, 2025 at 1:50 AM
Who are all you people searching for my thumbprint?!
July 21, 2025 at 3:12 PM
Maybe he was going for a Dreyfussian Man?
July 14, 2025 at 9:51 PM
As of today, I am officially Associate Professor* at @hcii.cmu.edu. Surreal — I was out of my depth when I started. Couldn't have done it without my incredible students — the true brains of the operation — and the support of my mentors. Thank you all!

* not yet tenured, because CMU
July 1, 2025 at 8:30 PM
Quite a notification from LinkedIn...@mmazurek.bsky.social
June 18, 2025 at 5:24 PM
📢 We now have two amazing keynote speakers lined up for #HAIPS2025 (the 1st Workshop on Human-Centered AI, Privacy, and Security)! @jas0nh0ng.bsky.social
and @pgk.bsky.social

Submit your:
- Original papers
- Encore papers
- SoK papers
- Vision papers

by June 20th!

💻http://haips.com
May 27, 2025 at 4:13 PM
😬In sims, 1/100 Asian-coded agents will join a protest if told they shouldn't. All 100 Black-coded agents will join anyway.

New #Facct2025 paper led by @yuxuanli1225.bsky.social
Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Models

sauvikdas.com/papers/64/se...
May 13, 2025 at 2:26 PM
En route to #chi2025!

1) Sunday: I will present a keynote talk at the computational UI workshop — the first public discussion of what we're doing at fuguUX, the company I'm co-founding with @jas0nh0ng.bsky.social
.

"Towards Smart, Automated UI Assessments at Scale"

1/3
April 25, 2025 at 5:12 PM
My third Ph.D. student, Jacob Logas, successfully defended his dissertation yesterday!

Jacob developed a framework for creating computationally aesthetic anti-facial recognition perturbations on images. Details to come!

He will be joining Franklin & Marshall as an assistant professor. Congrats!
April 12, 2025 at 8:01 PM
Hey look at that my 5yo already knows that 0-indexing is superior. This bodes well
March 8, 2025 at 11:56 PM
The scale of the problem is massive: An estimated 900 million* people worldwide own cryptocurrency, up from just 5M in 2016. Yet only 43% of crypto users in our survey with 643 participants could correctly identify a seed phrase from an image!

* www.statista.com/statistics/1...
March 3, 2025 at 4:10 PM
First, what's a seed phrase? It's a list of words (typically 24) that gives COMPLETE access to a “self-custodied” crypto wallet. This list of words can be used to derive the public/private keypair used to access one's crypto assets.

Many crypto users are utterly confused about what they are.
March 3, 2025 at 4:10 PM
📣 New research: Only 43% of 643 crypto users surveyed in our #CHI2025 study correctly identified a seed phrase from an image; 58% of those thought they choose their own, like a password. These, and other, misconceptions put these users at high risk.

Read the paper: sauvikdas.com/papers/63/se...

🧵👇
March 3, 2025 at 4:10 PM
Key findings: Users felt MORE concerned when:

- In public vs. private locations
- Permissions didn't match context expectations
- Apps requested sensitive permissions (camera, mic, calls)
February 26, 2025 at 2:22 PM
What does “concern” mean? We had participants rate both “concern” level and pick from a range of affective words that described their state. High concern was correlated with feeling “hostile” or “distressed”; low concern was correlated with feeling “indifferent” or “curious”.
February 26, 2025 at 2:22 PM
🔒 Our new #USEC2025 paper shows that by automating permission decisions based on prior decisions, we risk NORMALIZING privacy discomfort rather than reducing it.

"Modeling End-User Affective Discomfort With Mobile App Permissions"

Paper: sauvikdas.com/papers/60/se...
February 26, 2025 at 2:22 PM