Security, Privacy and Accountability in AI-Driven IoT Systems

Schedule & Reading List

Our sessions will take place every Thursday from 11:00 am to 1:00 pm (except 29th Oct). The first session will be held on 8th Oct, and the eighth (final) session will take place on 3rd Dec.

The first session will be an introductory lecture led entirely by the course convenors. Subsequent sessions will be structured as follows: the first part will consist of three 15—20 min presentations by course participants on the weekly papers, followed by a discussion of those papers in the second part.

Presentation schedule. Here is a fixed presentation schedule. Please make sure you know when you are presenting and which presentation flavour you have been assigned (advocate, balanced or critical).

Assignment Templates. For written assignments, you should follow the provided templates: review template and reflection template.

Week 1: IoT Threat Landscape

As this is the first lecture, you do not need to prepare any assignments for this week. The material below provides useful background reading on IoT threats, as well as articles with tips on reading and reviewing research papers that will be helpful for your assignments over the coming weeks.

• R267 Introduction Slides
• How to Read a Paper, Keshav, S. 2007. ACM SIGCOMM Computer Communication Review 37(3):83—84.
  [ DOI ]
• Writing Reviews for Systems Conferences, Roscoe, T. 2007. ETH Zürich.
  [ URL ]
• Dos and Don'ts of Machine Learning in Computer Security, Arp et al. 2022. 31st USENIX Security Symposium (USENIX Security '22), pp.3971—3988.
  [ URL ]
• Understanding the Mirai Botnet, Antonakakis et al. 2017. 26th USENIX Security Symposium (USENIX Security '17), pp.1093—1110.
  [ URL ]
• Information Exposure From Consumer IoT Devices, Ren et al. 2019. ACM Internet Measurement Conference (IMC).
  [ DOI ]
• SoK: Security Evaluation of Home-Based IoT Deployments, Alrawi et al. 2019. IEEE Symposium on Security and Privacy (S&P), pp.1362—1380.
  [ URL ]

Week 2: Voice Assistant Threats

• VoiceAttack: Fingerprinting Voice Command on VPN-protected Smart Home Speakers, Guo et al. 2024. ACM BuildSys.
  [ DOI ]
• Tracking, Profiling, and Ad Targeting in the Alexa Echo Smart Speaker Ecosystem, Iqbal et al. 2023. ACM Internet Measurement Conference (IMC).
  [ DOI ]
• Alexa versus Alexa: Controlling Smart Speakers by Self-Issuing Voice Commands, Esposito et al. 2022. ACM Asia Conference on Computer and Communications Security (AsiaCCS).
  [ DOI ]

Week 3: Network Inference

• WiFinger: Fingerprinting Noisy IoT Event Traffic Using Packet-level Sequence Matching, Li et al. 2026. Network and Distributed System Security Symposium (NDSS).
  [ URL ]
• BehavIoT: Measuring Smart Home IoT Behavior Using Network-Inferred Behavior Models, Hu et al. 2023. ACM Internet Measurement Conference (IMC).
  [ DOI ]
• Evaluating Machine Learning-Based IoT Device Identification Models for Security Applications, Maali et al. 2025. Network and Distributed System Security Symposium (NDSS).
  [ URL ]

Week 4: IoT Threat Detection

• CP-IoT: A Cross-Platform Monitoring System for Smart Home, Lin et al. 2024. Network and Distributed System Security Symposium (NDSS).
  [ URL ]
• A Lightweight IoT Cryptojacking Detection Mechanism in Heterogeneous Smart Home Networks, Tekiner et al. 2022. Network and Distributed System Security Symposium (NDSS).
  [ URL ]
• ARGUS: Context-Based Detection of Stealthy IoT Infiltration Attacks, Rieger et al. 2023. USENIX Security Symposium.
  [ URL ]

Week 5: Privacy Exposure and Auditing

• Lumos: Identifying and Localizing Diverse Hidden IoT Devices in an Unfamiliar Environment, Sharma et al. 2022. USENIX Security Symposium.
  [ URL ]
• Real-time Analysis of Privacy-(un)aware IoT Applications, Babun et al. 2021. Privacy Enhancing Technologies Symposium (PETS).
  [ URL ]
• Light Auditor: Power Measurement Can Tell Private Data Leakage through IoT Covert Channels, Jung et al. 2022. ACM Conference on Embedded Networked Sensor Systems (SenSys).
  [ DOI ]

Week 6: Privacy-Enhancing IoT

• PrivacyGuard: Enhancing Smart Home User Privacy, Yu et al. 2021. ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN).
  [ DOI ]
• iPET: Privacy Enhancing Traffic Perturbations for Secure IoT Communications, Shenoi et al. 2023. Privacy Enhancing Technologies Symposium (PETS).
  [ URL ]
• ObscureNet: Learning Attribute-invariant Latent Representation for Anonymizing Sensor Data, Hajihassani et al. 2021. ACM/IEEE Conference on Internet of Things Design and Implementation (IoTDI).
  [ DOI ]

Week 7: Verification and Accountability

• Evasion Attacks and Defenses on Smart Home Physical Event Verification, Ozmen et al. 2023. Network and Distributed System Security Symposium (NDSS).
  [ URL ]
• Are You Spying on Me? Large-Scale Analysis on IoT Data Exposure through Companion Apps, Nan et al. 2023. USENIX Security Symposium.
  [ URL ]
• Peekaboo: A Hub-Based Approach to Enable Transparency in Data Processing within Smart Homes, Jin et al. 2022. IEEE Symposium on Security and Privacy (S&P).
  [ URL ]

Week 8: Generative AI and IoT

• IoT-Brain: Grounding LLMs for Semantic-Spatial Sensor Scheduling, Zhou et al. 2026. ACM International Conference on Mobile Computing and Networking (MobiCom).
  [ URL ]
• Jailbreaking Embodied LLMs via Action-Level Manipulation, Huang et al. 2026. ACM/IEEE International Conference on Embedded Artificial Intelligence and Sensing Systems (SenSys).
  [ DOI ]
• TORCHLIGHT: Shedding LIGHT on Real-World Attacks on Cloudless IoT Devices Concealed within the Tor Network, Pan et al. 2025. USENIX Security Symposium.
  [ URL ]